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

    Neuronpedia

    INDEX
    Explanations

    organizations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     revanche
    -0.66
    ihnachten
    -0.66
     ब्रेकडाउन
    -0.65
     تانيه
    -0.64
     Himo
    -0.64
    ThroughAttribute
    -0.64
     mauva
    -0.63
     Reverso
    -0.61
     étoient
    -0.61
     AppColors
    -0.60
    POSITIVE LOGITS
     of
    0.83
     (
    0.60
    '
    0.59
    śnia
    0.52
    ,
    0.48
     leader
    0.45
     [
    0.45
     affiliates
    0.44
     flagship
    0.44
    readFileSync
    0.44
    Act Density 0.045%

    No Known Activations