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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -total
    -0.07
    ٤
    -0.07
    .tar
    -0.06
    (hdc
    -0.06
     관리
    -0.06
    었다
    -0.06
    conversation
    -0.06
    hus
    -0.06
    렸
    -0.06
     groin
    -0.06
    POSITIVE LOGITS
     Squ
    0.06
     prostituer
    0.06
     Brock
    0.06
    -ci
    0.06
    .imgur
    0.06
    alleries
    0.06
    EXIT
    0.06
    icas
    0.06
     Tun
    0.06
     Angel
    0.06
    Act Density 0.172%

    No Known Activations