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

    Neuronpedia

    INDEX
    Explanations

    having a, is sturdy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     webpack
    0.49
     inheritance
    0.47
     Veil
    0.46
     veil
    0.46
     food
    0.45
     kidney
    0.45
     U
    0.44
     bowel
    0.44
     shroud
    0.44
     fiber
    0.43
    POSITIVE LOGITS
     Од
    0.55
     Бри
    0.55
     մի
    0.54
     procé
    0.51
    厡
    0.51
    dincer
    0.49
     број
    0.48
    ਾ
    0.48
     ваше
    0.48
     тип
    0.48
    Act Density 0.000%

    No Known Activations