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

    Neuronpedia

    INDEX
    Explanations

    ification

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     conservatives
    -0.08
     Phen
    -0.08
     pupil
    -0.08
     Fleisch
    -0.07
    URG
    -0.07
     Instant
    -0.07
     ABS
    -0.07
     caliber
    -0.07
     instantaneous
    -0.07
     unanimous
    -0.07
    POSITIVE LOGITS
     diversification
    0.13
     diversified
    0.11
    Divers
    0.11
     diversify
    0.11
    ブログ
    0.10
     Divers
    0.10
    衡
    0.09
    аси
    0.08
     financed
    0.08
     развлеч
    0.08
    Act Density 0.008%

    No Known Activations