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

    Neuronpedia

    INDEX
    Explanations

    core loop

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     amely
    0.50
    em
    0.46
     wilayah
    0.45
     strapped
    0.45
    il
    0.45
    कार
    0.44
    empi
    0.44
    ol
    0.44
    inh
    0.44
     depan
    0.43
    POSITIVE LOGITS
     Commodity
    0.52
     Prejudice
    0.44
    сії
    0.43
     ڈیز
    0.43
    rocities
    0.43
     Comics
    0.43
     המש
    0.43
    orElse
    0.42
     aisément
    0.41
    ibilités
    0.41
    Act Density 0.002%

    No Known Activations