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

    Neuronpedia

    INDEX
    Explanations

    Code/technical documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Guidance
    -0.07
    ゼ
    -0.07
     المه
    -0.07
     Himself
    -0.06
     lights
    -0.06
    AP
    -0.06
    _student
    -0.06
    (Notification
    -0.06
     المو
    -0.06
     государ
    -0.06
    POSITIVE LOGITS
    .writeln
    0.06
    <bits
    0.06
    axes
    0.06
    �
    0.06
     допом
    0.06
    �
    0.06
    орту
    0.05
     nhanh
    0.05
    .Sin
    0.05
    .word
    0.05
    Act Density 0.000%

    No Known Activations