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

    Neuronpedia

    INDEX
    Explanations

    varied online discussions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .UseFont
    -0.07
    §
    -0.07
     pact
    -0.06
     assembly
    -0.06
     refuge
    -0.06
     Broadcom
    -0.06
    とはい
    -0.06
     carefully
    -0.06
    㽏
    -0.06
    基地
    -0.06
    POSITIVE LOGITS
    _advance
    0.08
     boosting
    0.07
    ログ
    0.07
    oub
    0.06
    ancer
    0.06
     pornstar
    0.06
    وير
    0.06
    rogen
    0.06
    .png
    0.06
    ndon
    0.06
    Act Density 0.209%

    No Known Activations