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

    Neuronpedia

    INDEX
    Explanations

    surgery

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     optic
    -0.07
     Attacks
    -0.07
     रहत
    -0.07
    arg
    -0.06
    egers
    -0.06
     Estimate
    -0.06
    ‌ال
    -0.06
    -category
    -0.06
     دنیا
    -0.06
     teachings
    -0.06
    POSITIVE LOGITS
     lud
    0.06
    CLUDE
    0.06
    Omega
    0.06
    stackpath
    0.06
     punish
    0.06
    :,
    0.06
     Zu
    0.05
    .Username
    0.05
    (fig
    0.05
    ocoder
    0.05
    Act Density 0.008%

    No Known Activations