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

    Neuronpedia

    INDEX
    Explanations

    fake SSL certificate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    financ
    0.82
    getItems
    0.71
    श्किल
    0.66
    Dance
    0.63
     사건
    0.63
     einzigen
    0.63
    Criminal
    0.63
    Wage
    0.63
    𝘤
    0.63
    อะไร
    0.63
    POSITIVE LOGITS
     pre
    0.68
     varying
    0.67
     generally
    0.65
     predicted
    0.64
     usually
    0.64
     both
    0.63
     proximal
    0.63
     whether
    0.61
    สำหรับการ
    0.61
     potential
    0.61
    Act Density 0.001%

    No Known Activations