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

    Neuronpedia

    INDEX
    Explanations

    HTML/code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dims
    -0.07
     七
    -0.07
    Distribution
    -0.07
    leanor
    -0.06
    杜
    -0.06
     Falcon
    -0.06
    .validators
    -0.06
     giants
    -0.06
     consistent
    -0.06
    広
    -0.06
    POSITIVE LOGITS
    Hello
    0.06
    OfSize
    0.06
    .edit
    0.06
    .setImage
    0.06
    clado
    0.06
    .SelectedValue
    0.06
     yöntem
    0.06
    rnek
    0.06
     Tarih
    0.06
    (=
    0.06
    Act Density 0.126%

    No Known Activations