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

    Neuronpedia

    INDEX
    Explanations

    rules/constraints

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _boxes
    -0.07
    imgs
    -0.07
     preco
    -0.07
     prevState
    -0.07
    -message
    -0.06
     Burns
    -0.06
    izzes
    -0.06
    .analysis
    -0.06
    .Source
    -0.06
    iration
    -0.06
    POSITIVE LOGITS
    geber
    0.07
    -region
    0.06
    WSTR
    0.06
    ermo
    0.06
    Am
    0.06
    ,key
    0.06
    COL
    0.06
    ảo
    0.06
     ey
    0.06
    Describe
    0.06
    Act Density 0.006%

    No Known Activations