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

    Neuronpedia

    INDEX
    Explanations

    claim

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ApiService
    -0.07
     Cannes
    -0.07
    _SUP
    -0.06
     habits
    -0.06
     Manitoba
    -0.06
    actor
    -0.06
    Overview
    -0.06
    012
    -0.06
     plusieurs
    -0.06
    ボ
    -0.05
    POSITIVE LOGITS
     says
    0.07
     preaching
    0.07
     headline
    0.07
    Literal
    0.06
    ;",↵
    0.06
    عة
    0.06
    iền
    0.06
     Fetish
    0.06
    ật
    0.06
    MakeRange
    0.06
    Act Density 0.004%

    No Known Activations