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

    Neuronpedia

    INDEX
    Explanations

    Charles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    📨
    -0.08
    (mappedBy
    -0.08
    .lucene
    -0.08
    landırıl
    -0.07
     kcal
    -0.07
    רוך
    -0.07
    狞
    -0.07
    inté
    -0.07
    [loc
    -0.07
    🦖
    -0.07
    POSITIVE LOGITS
    鞋
    0.08
    	self
    0.08
    Batch
    0.08
     crossing
    0.07
    over
    0.07
    good
    0.07
    _STA
    0.07
    ensive
    0.07
    ':
    0.07
    ay
    0.07
    Act Density 0.002%

    No Known Activations