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

    Neuronpedia

    INDEX
    Explanations

    switch usage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     видим
    0.89
     drawed
    0.77
    uais
    0.75
     unem
    0.75
    ியுள்ள
    0.74
     beve
    0.73
    éu
    0.72
     celulares
    0.72
     internacionais
    0.72
     fünf
    0.71
    POSITIVE LOGITS
     מח
    0.73
     champ
    0.67
    Less
    0.66
    нні
    0.66
     বি
    0.65
     sustenance
    0.64
     월
    0.64
     meno
    0.63
    ন
    0.63
    Champ
    0.63
    Act Density 0.000%

    No Known Activations