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

    Neuronpedia

    INDEX
    Explanations

    variables

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _DEL
    -0.07
     vlád
    -0.07
    )>=
    -0.06
     úspěš
    -0.06
    ощи
    -0.06
    ombat
    -0.06
     }),
    -0.06
     +=
    -0.06
    زینه
    -0.06
    ضاء
    -0.06
    POSITIVE LOGITS
     straight
    0.07
    Sept
    0.06
    (ident
    0.06
    监听页面
    0.06
    _axes
    0.06
     trademarks
    0.06
     "^
    0.06
     membrane
    0.06
     ta
    0.06
    160
    0.06
    Act Density 0.000%

    No Known Activations