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

    Neuronpedia

    INDEX
    Explanations

    youtube links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Truth
    0.73
     zumindest
    0.71
     bestand
    0.70
     <-
    0.69
     कुर
    0.67
    <-
    0.66
     ç
    0.65
     sü
    0.65
     autop
    0.65
    ?
    0.65
    POSITIVE LOGITS
     fabricating
    0.78
    ОВА
    0.70
     Fabric
    0.67
    ক্ষণিক
    0.65
    শিষ্ট
    0.65
    挍
    0.65
    ಲ್‌
    0.65
    अफ
    0.65
    ವಾಗಿರುತ್ತದೆ
    0.64
    醺
    0.64
    Act Density 0.001%

    No Known Activations