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

    Neuronpedia

    INDEX
    Explanations

    general miscellaneous

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Declan
    0.64
    wx
    0.62
     Dog
    0.60
     Detail
    0.60
     Dean
    0.58
    Detail
    0.57
     Detailed
    0.56
     Occupational
    0.55
     tag
    0.55
     detailed
    0.54
    POSITIVE LOGITS
     रास्ते
    0.59
     باستخدام
    0.58
     kumb
    0.56
     Circuits
    0.56
    सिल
    0.55
    pixels
    0.55
    ampions
    0.55
    jaman
    0.54
    zipped
    0.54
     tillsammans
    0.54
    Act Density 0.000%

    No Known Activations