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

    Neuronpedia

    INDEX
    Explanations

    break down

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     NE
    0.71
     EPS
    0.70
     contradicts
    0.69
     awalnya
    0.66
     fonds
    0.66
     inaccur
    0.63
     anecd
    0.63
     नामक
    0.63
     uitvo
    0.62
     initially
    0.61
    POSITIVE LOGITS
    aquest
    0.82
    это
    0.80
    di
    0.77
    de
    0.76
    this
    0.75
    as
    0.74
    ffield
    0.73
    awk
    0.72
    asă
    0.72
    ield
    0.71
    Act Density 0.001%

    No Known Activations