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

    Neuronpedia

    INDEX
    Explanations

    list item marker 'A'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    t
    1.34
    r
    1.27
    a
    1.23
    ని
    1.16
    f
    1.07
    til
    1.03
    на
    1.03
    s
    1.02
    ম
    1.01
    d
    0.99
    POSITIVE LOGITS
     veces
    1.77
    varage
    1.74
     partir
    1.66
    ktionen
    1.65
     priori
    1.65
    FFECT
    1.63
     través
    1.60
     thaliana
    1.59
    uparavant
    1.54
    pathetic
    1.52
    Act Density 0.236%

    No Known Activations