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

    Neuronpedia

    INDEX
    Explanations

    references to community involvement and collaboration

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

    Tokens after commas or conjunctions

    np_acts-logits-general · gemini-2.0-flash

    groups of people and entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     >=",
    -0.73
    Życiorys
    -0.68
     للاسماء
    -0.64
     صوتيه
    -0.61
     Audiodateien
    -0.60
    舺
    -0.60
    ToTop
    -0.57
    thâu
    -0.57
    MigrationBuilder
    -0.56
     kaarangay
    -0.55
    POSITIVE LOGITS
     their
    0.78
     families
    0.77
     ourselves
    0.75
     myself
    0.72
     yourself
    0.69
     parents
    0.67
     themselves
    0.66
    themselves
    0.66
     spouses
    0.66
     visitors
    0.65
    Act Density 0.310%

    No Known Activations