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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kaçtır
    0.66
    ᱲ
    0.63
    nobyl
    0.62
    localVarHTTP
    0.61
    zing
    0.60
    சன்
    0.60
    ANCED
    0.58
    oforte
    0.57
    oucí
    0.57
    炅
    0.57
    POSITIVE LOGITS
     рису
    0.65
     jersey
    0.64
    মনে
    0.64
    কে
    0.64
     delimiters
    0.64
     expansion
    0.63
    カタログ
    0.63
    クラス
    0.62
     mixture
    0.62
    োপুরি
    0.62
    Act Density 1.370%

    No Known Activations