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

    Neuronpedia

    INDEX
    Explanations

    damage

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     MAT
    -0.06
     Inspiration
    -0.06
    $rows
    -0.06
     道
    -0.06
     Masc
    -0.06
    зна
    -0.06
    �
    -0.06
     mappings
    -0.06
     chua
    -0.06
    CHOOL
    -0.06
    POSITIVE LOGITS
    .reset
    0.07
     komple
    0.07
    ')↵↵↵↵
    0.07
     todd
    0.07
    ])↵↵↵
    0.07
    pipe
    0.06
    ulur
    0.06
     crippling
    0.06
     reducer
    0.06
    !important
    0.06
    Act Density 0.204%

    No Known Activations