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

    Neuronpedia

    INDEX
    Explanations

    AI chatbots and character AI

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     perimeter
    0.57
     kahe
    0.55
     Parigi
    0.54
     trigonometric
    0.53
     percorso
    0.53
    收聽
    0.53
    氏は
    0.51
     squeeze
    0.51
     piz
    0.50
    鶘
    0.50
    POSITIVE LOGITS
    this
    0.75
    to
    0.70
    Т
    0.68
    of
    0.67
    Index
    0.65
    1
    0.63
    cı
    0.62
    Splash
    0.62
    it
    0.61
    target
    0.61
    Act Density 0.000%

    No Known Activations