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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Bas
    -0.07
    Smith
    -0.07
    Guard
    -0.07
    Entry
    -0.07
    .allowed
    -0.06
    Psy
    -0.06
     vn
    -0.06
    twenty
    -0.06
    );↵↵
    -0.06
     MQ
    -0.06
    POSITIVE LOGITS
     الض
    0.07
     симптом
    0.07
     الأك
    0.07
     Sugar
    0.07
    ']."'
    0.07
     ModelState
    0.07
    rijk
    0.07
     руковод
    0.07
    (bs
    0.07
    ？」
    0.07
    Act Density 0.005%

    No Known Activations