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

    Neuronpedia

    INDEX
    Explanations

    promotion

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    "<?
    -0.07
     کنیم
    -0.06
     Sv
    -0.06
     getLast
    -0.06
    ?>><?
    -0.06
     metavar
    -0.06
    eceğiz
    -0.06
     أخرى
    -0.06
    steady
    -0.06
     Magical
    -0.06
    POSITIVE LOGITS
     personally
    0.07
    _error
    0.07
    _observer
    0.07
    primaryKey
    0.07
    _bind
    0.06
    _PERCENT
    0.06
    Collapsed
    0.06
     سیستم
    0.06
     discrepancy
    0.06
     퍼
    0.06
    Act Density 0.001%

    No Known Activations