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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _PATCH
    -0.08
    ARGIN
    -0.07
    _upload
    -0.07
    _sb
    -0.07
    .Types
    -0.06
     nerve
    -0.06
     چهار
    -0.06
    _LEVEL
    -0.06
     UNU
    -0.06
     Aynı
    -0.06
    POSITIVE LOGITS
     Mutation
    0.07
     pretend
    0.06
     autour
    0.06
     extractor
    0.06
    utschen
    0.06
    �认
    0.06
     pretending
    0.06
     adul
    0.06
     astounding
    0.06
    	Scanner
    0.06
    Act Density 0.000%

    No Known Activations