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

    Neuronpedia

    INDEX
    Explanations

    code punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _Row
    -0.06
    000
    -0.06
    _CAST
    -0.06
    Weak
    -0.06
     repeated
    -0.06
    649
    -0.06
    uib
    -0.06
     робити
    -0.06
    Ngày
    -0.06
    答案
    -0.06
    POSITIVE LOGITS
     dout
    0.07
     exploding
    0.07
     nichts
    0.07
     бог
    0.07
    illon
    0.07
     zorunda
    0.06
     oč
    0.06
    ریب
    0.06
    .HasValue
    0.06
    اهم
    0.06
    Act Density 0.201%

    No Known Activations