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

    Neuronpedia

    INDEX
    Explanations

    afraid

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     SSA
    -0.07
     degree
    -0.06
    (source
    -0.06
    ocaust
    -0.06
     Zust
    -0.06
    DeltaTime
    -0.06
     Kant
    -0.06
    .RegisterType
    -0.06
     상태
    -0.06
    得到
    -0.06
    POSITIVE LOGITS
    _candidate
    0.08
    .Topic
    0.08
    .dependencies
    0.07
     現
    0.07
     scare
    0.06
    HasColumnType
    0.06
    .Data
    0.06
     fearless
    0.06
    ><![
    0.06
     dancer
    0.06
    Act Density 0.012%

    No Known Activations