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

    Neuronpedia

    INDEX
    Explanations

    Phone specifications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Kawasaki
    -0.08
    _Key
    -0.07
     Marian
    -0.07
     unnoticed
    -0.07
    _walk
    -0.07
     populist
    -0.07
     mommy
    -0.07
     Champ
    -0.06
    ()<<"
    -0.06
     Brown
    -0.06
    POSITIVE LOGITS
    ώρα
    0.06
    .inc
    0.06
    .templates
    0.06
     elems
    0.06
     allot
    0.06
     pequ
    0.06
    няв
    0.05
    FXML
    0.05
     iyileş
    0.05
    .↵↵↵↵↵↵
    0.05
    Act Density 0.020%

    No Known Activations