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

    Neuronpedia

    INDEX
    Explanations

    the rise of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ors
    0.56
    ie
    0.48
    ä
    0.48
    í
    0.47
    im
    0.44
     likelihood
    0.43
    র্ঘ
    0.40
    u
    0.40
    on
    0.39
    Miss
    0.39
    POSITIVE LOGITS
    к
    0.63
     buah
    0.53
    ciences
    0.52
     desirous
    0.51
     Dif
    0.50
     deprec
    0.50
    തമായ
    0.50
     zealand
    0.50
     часа
    0.50
     glycine
    0.50
    Act Density 0.045%

    No Known Activations