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

    Neuronpedia

    INDEX
    Explanations

    descriptive words after "and"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     они
    0.54
     autori
    0.52
    graphHead
    0.51
     écrire
    0.50
     escre
    0.50
     essi
    0.50
     sogen
    0.49
     eux
    0.48
     explique
    0.48
    udrait
    0.48
    POSITIVE LOGITS
    ED
    0.75
    K
    0.69
    T
    0.68
    R
    0.66
    z
    0.66
    F
    0.63
     an
    0.62
    A
    0.61
    EL
    0.61
    P
    0.59
    Act Density 0.008%

    No Known Activations