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

    Neuronpedia

    INDEX
    Explanations

    name

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    аток
    -0.07
    pol
    -0.07
    _closure
    -0.07
     Dash
    -0.07
    rections
    -0.07
    Cal
    -0.07
     populations
    -0.07
    CAD
    -0.07
     philosophy
    -0.06
     Imported
    -0.06
    POSITIVE LOGITS
     آی
    0.07
    WithName
    0.06
     쉬
    0.06
     grave
    0.06
    (page
    0.06
     воздуха
    0.06
     eget
    0.06
    |{↵
    0.06
    .volley
    0.06
    .define
    0.06
    Act Density 0.014%

    No Known Activations