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

    Neuronpedia

    INDEX
    Explanations

    column

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     column
    -0.69
     meaning
    -0.60
     yes
    -0.51
    meaning
    -0.49
    Jîn
    -0.49
    brü
    -0.47
    InteropServices
    -0.47
     Meaning
    -0.46
     Across
    -0.45
    tetés
    -0.44
    POSITIVE LOGITS
    ing
    0.77
    InputTagHelper
    0.68
    tubers
    0.63
    tieth
    0.62
    pence
    0.60
    isier
    0.59
    nadequate
    0.59
    ingale
    0.58
    numerusform
    0.58
    stdc
    0.56
    Act Density 0.026%

    No Known Activations