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

    Neuronpedia

    INDEX
    Explanations

    origin

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Write
    -0.07
     Last
    -0.07
     routers
    -0.07
     $
    -0.06
    _save
    -0.06
    Last
    -0.06
    /File
    -0.06
     BK
    -0.06
    _CALC
    -0.06
    ('/')↵
    -0.06
    POSITIVE LOGITS
     origin
    0.07
    ocus
    0.07
    ีพ
    0.06
    غط
    0.06
    ertia
    0.06
     üzer
    0.06
     нав
    0.06
    味
    0.06
    ीन
    0.06
     uso
    0.06
    Act Density 0.004%

    No Known Activations