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

    Neuronpedia

    INDEX
    Explanations

    UI layout constraints

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .nome
    -0.07
    ョ
    -0.06
    .↵↵
    -0.06
     fox
    -0.06
    hsi
    -0.06
     nightlife
    -0.06
     Pride
    -0.06
     attractions
    -0.06
    ..↵↵
    -0.06
    (Matrix
    -0.06
    POSITIVE LOGITS
     define
    0.07
     Policies
    0.07
    膜
    0.07
     pand
    0.06
    predicted
    0.06
    ;-
    0.06
     notes
    0.06
    備
    0.06
    assist
    0.06
    COMMENT
    0.06
    Act Density 0.002%

    No Known Activations