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

    Neuronpedia

    INDEX
    Explanations

    relies entirely

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    વામાં
    0.44
     embellished
    0.39
    ocam
    0.39
    漢字
    0.39
     ThinQ
    0.38
     戦
    0.37
    उँ
    0.36
     نسب
    0.36
    unque
    0.36
     Death
    0.36
    POSITIVE LOGITS
     மிசோ
    0.39
    Muscle
    0.38
     misdemeanor
    0.36
    Myers
    0.36
    UnitPrice
    0.36
    rieved
    0.35
     musia
    0.35
     integrator
    0.35
     entirely
    0.35
     signaled
    0.35
    Act Density 0.001%

    No Known Activations