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

    Neuronpedia

    INDEX
    Explanations

    options and descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Karite
    0.49
     Headache
    0.48
     दुआ
    0.46
     Defts
    0.45
     Antwort
    0.45
    AxisSize
    0.45
     Gaut
    0.44
    苓
    0.44
     Metabolic
    0.44
     Nash
    0.44
    POSITIVE LOGITS
    ඬ
    0.45
    ин
    0.44
    World
    0.43
    ᱧ
    0.43
    на
    0.42
    и
    0.42
    リ
    0.42
    Ру
    0.42
    매
    0.41
    in
    0.41
    Act Density 0.001%

    No Known Activations