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

    Neuronpedia

    INDEX
    Explanations

    academic writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ्यार
    -0.08
     cancellation
    -0.08
     Canc
    -0.08
    _Start
    -0.07
     preparation
    -0.07
    Canc
    -0.07
     xl
    -0.07
     Cancellation
    -0.07
    	Start
    -0.07
     Telescope
    -0.07
    POSITIVE LOGITS
    blockquote
    0.09
    引用
    0.08
     gloss
    0.08
     Aussagen
    0.08
    Annot
    0.08
    哪个
    0.08
     referencing
    0.08
     cites
    0.08
     לט
    0.08
     absorb
    0.08
    Act Density 0.019%

    No Known Activations