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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     expectations
    -0.07
     scp
    -0.07
     ult
    -0.07
    ावन
    -0.06
    _meta
    -0.06
    	LOG
    -0.06
    たく
    -0.06
     sj
    -0.06
    Immutable
    -0.06
     Amber
    -0.06
    POSITIVE LOGITS
    (posts
    0.07
    getDoctrine
    0.06
     visite
    0.06
    üf
    0.06
    %%%%%%%%%%%%%%%%
    0.06
     Vide
    0.06
     ビ
    0.06
    PRI
    0.06
     série
    0.06
    -null
    0.06
    Act Density 0.020%

    No Known Activations