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
     artery
    -0.07
     ser
    -0.07
    287
    -0.07
    744
    -0.07
     א
    -0.07
     hoses
    -0.07
     заяв
    -0.07
    jsx
    -0.06
    těl
    -0.06
     manner
    -0.06
    POSITIVE LOGITS
     Hawth
    0.07
     espos
    0.06
    Feat
    0.06
    求
    0.06
     kz
    0.06
     Toshiba
    0.06
    \↵
    0.06
    ::↵
    0.06
    ा.↵
    0.06
    Denver
    0.06
    Act Density 0.043%

    No Known Activations