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

    Neuronpedia

    INDEX
    Explanations

    the word "both" (case insensitive) in the text

    oai_token-act-pair · gemini-2.0-flash

    both

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    SourceChecksum
    -0.91
    SequentialGroup
    -0.71
    الإنجليزية
    -0.65
     referenties
    -0.65
    elemField
    -0.63
     myſelf
    -0.61
     Houſe
    -0.60
     juſt
    -0.60
    PMailer
    -0.60
     houſe
    -0.59
    POSITIVE LOGITS
    CloseOperation
    0.62
    AccessException
    0.62
     those
    0.57
    RESPOND
    0.54
    ricultural
    0.54
     these
    0.53
    agama
    0.53
    CHORUS
    0.52
    rogly
    0.51
    holms
    0.50
    Act Density 2.303%

    No Known Activations