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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    GUILayout
    -0.07
     também
    -0.07
    库
    -0.06
    odos
    -0.06
     створ
    -0.06
    Connections
    -0.06
     sử
    -0.06
    .keys
    -0.06
    fy
    -0.06
     penal
    -0.06
    POSITIVE LOGITS
     Ün
    0.08
    Tôi
    0.06
     aile
    0.06
    .Form
    0.06
     Gather
    0.06
    .Nome
    0.06
    ircuit
    0.06
     MODIFY
    0.06
    _continuous
    0.06
     coordin
    0.06
    Act Density 0.110%

    No Known Activations