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

    Neuronpedia

    INDEX
    Explanations

    sentences that include monetary amounts or compensation

    oai_token-act-pair · gemini-2.0-flash

    Number six

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Roskov
    -0.64
    ьаж
    -0.61
    timewa
    -0.61
    unknownFields
    -0.58
     palmas
    -0.57
    localctx
    -0.56
    клопе
    -0.56
    TagMode
    -0.55
    StoryboardSegue
    -0.55
    XmlAccessType
    -0.54
    POSITIVE LOGITS
     six
    1.60
    six
    1.36
     Six
    1.31
     seven
    1.31
    Six
    1.23
     SIX
    1.10
     sechs
    1.07
    seven
    1.05
     seis
    1.05
     шести
    1.02
    Act Density 1.582%

    No Known Activations