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

    Neuronpedia

    INDEX
    Explanations

    terms related to insurance and financial risk management

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

    preceding predictive or comparative choices

    np_acts-logits-general · gemini-2.0-flash

    options, choice, premium, access

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hitherto
    -0.76
     retarded
    -0.69
     läßt
    -0.67
     advices
    -0.67
     наверное
    -0.66
     !!!!
    -0.65
     skall
    -0.64
     видимо
    -0.63
     Надо
    -0.62
     envisaged
    -0.61
    POSITIVE LOGITS
    Trusted
    0.90
     aren
    0.89
     isn
    0.88
     nahilalakip
    0.86
    ⏤
    0.79
     ⁠
    0.77
     your
    0.75
    mdash
    0.74
    —”
    0.73
    ꟷ
    0.73
    Act Density 0.335%

    No Known Activations