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

    Neuronpedia

    INDEX
    Explanations

    best

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     VECTOR
    -0.07
    Marco
    -0.07
     Parameter
    -0.06
     Ug
    -0.06
     ethnic
    -0.06
    Grid
    -0.06
     graf
    -0.06
     invariant
    -0.06
    blocks
    -0.06
     prosecuting
    -0.06
    POSITIVE LOGITS
     Authorization
    0.06
     않을
    0.06
     �
    0.06
     하고
    0.06
     pourquoi
    0.06
     あ
    0.06
    .pushButton
    0.06
     Bedrooms
    0.06
    違い
    0.06
    HeaderInSection
    0.06
    Act Density 0.033%

    No Known Activations