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

    Neuronpedia

    INDEX
    Explanations

    gravity stress

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    انی
    0.58
     ję
    0.55
    ULONG
    0.53
    holomorphic
    0.50
     nField
    0.50
    Identity
    0.48
    Hindi
    0.47
    IsResolver
    0.46
    ASDW
    0.46
     जाणून
    0.46
    POSITIVE LOGITS
     that
    0.48
     you
    0.47
     Model
    0.46
     "
    0.45
     the
    0.43
     Apples
    0.43
    Modelo
    0.42
     v
    0.41
     LE
    0.41
     cima
    0.41
    Act Density 0.004%

    No Known Activations