Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    verbs and constructs related to personal experiences and feelings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Follows "is," "was," or "'s."

    np_acts-logits-general · gemini-2.0-flash

    is, was, be, or proof/missing followed by common words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.71
     brio
    -0.56
    Herzliche
    -0.53
    twimg
    -0.51
     diminution
    -0.51
     Desta
    -0.50
     invid
    -0.50
     Implicit
    -0.50
     تس
    -0.49
    ंदीखरीदारी
    -0.49
    POSITIVE LOGITS
     compréhen
    0.69
     prouver
    0.68
     honestly
    0.67
     something
    0.66
     definitely
    0.65
    addGap
    0.63
    ungkinan
    0.61
     quelcon
    0.61
     végétal
    0.60
    migrationBuilder
    0.59
    Act Density 0.272%

    No Known Activations