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

    Neuronpedia

    INDEX
    Explanations

    storage limitation video

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     squash
    0.57
     ver
    0.55
    ိန်
    0.55
     rifle
    0.54
     vultures
    0.54
     upscale
    0.53
     padres
    0.53
     arcane
    0.52
    ஜ்
    0.52
     young
    0.51
    POSITIVE LOGITS
     Terbaik
    0.65
     Луч
    0.57
     Passwort
    0.57
     પ્રકાશ
    0.55
    Iv
    0.54
    泞
    0.54
     пора
    0.54
     충
    0.53
    ＰＥＮＡＮＡ
    0.53
    Content
    0.52
    Act Density 0.001%

    No Known Activations