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

    Neuronpedia

    INDEX
    Explanations

    wide

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Vers
    -0.07
    <?,
    -0.07
    }.{
    -0.06
     flows
    -0.06
    );↵
    -0.06
     stages
    -0.06
     asks
    -0.06
    _,
    -0.06
    转化为
    -0.06
    はどう
    -0.06
    POSITIVE LOGITS
     Debate
    0.08
     Recorder
    0.08
    ewhat
    0.07
     đình
    0.07
     Ông
    0.07
    戒
    0.07
    คณะกรรมการ
    0.07
    信念
    0.07
    .all
    0.07
     Minority
    0.07
    Act Density 0.010%

    No Known Activations