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

    Neuronpedia

    INDEX
    Explanations

    path

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     infectious
    -0.07
    -piece
    -0.07
    Atomic
    -0.07
     Bolshevik
    -0.06
    ={↵
    -0.06
     Composition
    -0.06
    (tile
    -0.06
    .Instance
    -0.06
    control
    -0.06
    做到
    -0.06
    POSITIVE LOGITS
     admin
    0.08
    ipmap
    0.07
    �
    0.07
    🔎
    0.07
    ителей
    0.06
     webView
    0.06
    못
    0.06
     chấp
    0.06
    _CLICKED
    0.06
    �
    0.06
    Act Density 0.003%

    No Known Activations