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

    Neuronpedia

    INDEX
    Explanations

    =

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Exc
    -0.07
    patterns
    -0.07
    衝
    -0.07
    �
    -0.07
     above
    -0.07
    lector
    -0.06
     populated
    -0.06
    ערה
    -0.06
    מפקד
    -0.06
     impressed
    -0.06
    POSITIVE LOGITS
    guna
    0.07
     elastic
    0.07
    zhou
    0.07
    会导致
    0.07
     sublicense
    0.07
    (QString
    0.06
     duration
    0.06
    ");//
    0.06
     IReadOnly
    0.06
    )*(
    0.06
    Act Density 0.021%

    No Known Activations