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

    Neuronpedia

    INDEX
    Explanations

    purpose and tasks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.46
     Rass
    0.41
    Files
    0.41
    love
    0.41
    ↵
    0.40
    Fin
    0.40
     $
    0.40
    Passport
    0.39
    club
    0.39
     ይቀ
    0.39
    POSITIVE LOGITS
    ленных
    0.67
    ских
    0.60
     etcétera
    0.60
    .??.??"]
    0.53
    كيت
    0.52
    ленный
    0.52
    ским
    0.51
    唪
    0.51
    нных
    0.50
     movimientos
    0.50
    Act Density 0.003%

    No Known Activations