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

    Neuronpedia

    INDEX
    Explanations

    court judgements and rulings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    assati
    0.59
    ς
    0.57
    W
    0.57
    ન
    0.55
    Wildlife
    0.53
    mf
    0.52
    Z
    0.51
    A
    0.50
    EXAMPLE
    0.49
    지
    0.49
    POSITIVE LOGITS
     buenos
    0.64
     française
    0.62
     österreich
    0.61
     भारता
    0.58
    国
    0.58
    大学
    0.57
     OMG
    0.57
     sebagai
    0.57
     vitally
    0.56
     impresionante
    0.56
    Act Density 0.002%

    No Known Activations