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

    Neuronpedia

    INDEX
    Explanations

    references to legal terms and case law

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

    Numbers followed by a digit

    np_acts-logits-general · gemini-2.0-flash

    forty or four

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    6
    -0.96
     six
    -0.90
     Six
    -0.89
     sixth
    -0.82
    7
    -0.79
     Sixth
    -0.76
     seven
    -0.74
    六
    -0.73
    Six
    -0.71
     SIX
    -0.70
    POSITIVE LOGITS
     Forty
    0.77
     forty
    0.72
     keempat
    0.65
    forty
    0.64
    Forty
    0.63
    4
    0.63
    ４
    0.63
     Four
    0.61
     four
    0.60
    四十
    0.60
    Act Density 0.811%

    No Known Activations