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

    Neuronpedia

    INDEX
    Explanations

    us

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .aw
    -0.08
    .running
    -0.08
    ANCES
    -0.08
     running
    -0.07
    'at
    -0.07
    ANCE
    -0.07
    ============================================================================
    -0.07
    LETE
    -0.07
     زی
    -0.07
    ::::::::::::::::
    -0.07
    POSITIVE LOGITS
    abe
    0.08
    �
    0.08
    �运
    0.08
    ाको
    0.07
     Revel
    0.07
    ็บ
    0.07
    ��
    0.07
     commercial
    0.07
    Bright
    0.07
     dto
    0.07
    Act Density 0.162%

    No Known Activations