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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    舉
    -0.07
    ﺘ
    -0.07
     famed
    -0.07
     Mixing
    -0.06
    :host
    -0.06
    Evento
    -0.06
     produto
    -0.06
    очатку
    -0.06
     Coding
    -0.06
    碎
    -0.06
    POSITIVE LOGITS
    221
    0.07
     rootView
    0.06
    StringValue
    0.06
    elope
    0.06
    441
    0.06
     Paladin
    0.06
    音
    0.06
    <Text
    0.06
    hlas
    0.06
     RuntimeMethod
    0.06
    Act Density 0.001%

    No Known Activations