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

    Neuronpedia

    INDEX
    Explanations

    assistant

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pédicule
    0.66
     tathapi
    0.60
    7
    0.60
     cuerpos
    0.59
     déplacer
    0.59
    4
    0.59
    collider
    0.59
    ियाँ
    0.59
     porém
    0.59
     zvuk
    0.58
    POSITIVE LOGITS
     for
    0.84
    an
    0.75
    ad
    0.73
     Easy
    0.64
     in
    0.64
    ש
    0.63
    ون
    0.62
     Add
    0.61
     Activities
    0.61
    el
    0.61
    Act Density 0.209%

    No Known Activations