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

    Neuronpedia

    INDEX
    Explanations

    location or extent

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     [{"
    0.64
     kabhi
    0.63
     deduction
    0.61
     venant
    0.61
     evasion
    0.61
     решили
    0.61
     revelation
    0.60
     confidentiality
    0.59
    जयपुर
    0.59
     EventHandler
    0.58
    POSITIVE LOGITS
     sırada
    0.70
    ης
    0.69
    tion
    0.68
     bulunduğu
    0.67
    tained
    0.66
    daniel
    0.64
    TP
    0.63
    C
    0.62
    virk
    0.62
    ر
    0.62
    Act Density 0.133%

    No Known Activations