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

    Neuronpedia

    INDEX
    Explanations

    here live, shock value

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     simplest
    0.46
     Give
    0.45
     Students
    0.41
     Kaw
    0.41
    车
    0.41
     Maestro
    0.41
     जिसमें
    0.40
     Speaker
    0.40
    }])
    0.40
     Myst
    0.39
    POSITIVE LOGITS
    UMPS
    0.43
    Results
    0.42
    WORK
    0.39
     upsetting
    0.39
    kBtu
    0.39
     exposing
    0.38
    ecal
    0.38
     rubles
    0.38
     উপদেশ
    0.38
    tuples
    0.38
    Act Density 0.000%

    No Known Activations