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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    LineNumber
    -0.08
    _ACTIVE
    -0.07
    Když
    -0.06
     VIEW
    -0.06
    thora
    -0.06
     Když
    -0.06
    μη
    -0.06
    ToSelector
    -0.06
    जह
    -0.06
    κυ
    -0.06
    POSITIVE LOGITS
    !),
    0.07
    犬
    0.07
    	labels
    0.07
    Whilst
    0.07
    帝国
    0.06
    _origin
    0.06
    ,↵
    0.06
     using
    0.06
    (src
    0.06
     reported
    0.06
    Act Density 0.066%

    No Known Activations