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

    Neuronpedia

    INDEX
    Explanations

    Neanderthal and organization

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    䀖
    0.96
    觟
    0.91
    ᅨ
    0.89
    rocyte
    0.87
     gladly
    0.87
    හෝ
    0.86
    牪
    0.86
     każde
    0.86
    䞍
    0.85
    步伐
    0.84
    POSITIVE LOGITS
    ر
    0.71
    bark
    0.65
    an
    0.62
     BC
    0.61
    ن
    0.60
     Resource
    0.60
    BES
    0.60
    '
    0.59
    لود
    0.59
     H
    0.59
    Act Density 0.005%

    No Known Activations