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

    Neuronpedia

    INDEX
    Explanations

    need for help or fixing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     லட்ச
    0.46
     Arsen
    0.44
     persyaratan
    0.42
     prepares
    0.42
    getTransforms
    0.42
     பக்தர்கள்
    0.42
    परेट
    0.41
    ்தான்
    0.41
    တင်း
    0.40
     insists
    0.40
    POSITIVE LOGITS
    FlightID
    0.36
    WC
    0.36
     його
    0.36
     real
    0.34
     Now
    0.34
     njega
    0.34
    腿
    0.34
     ноги
    0.33
     HOT
    0.33
     недели
    0.33
    Act Density 0.000%

    No Known Activations