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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     temper
    -0.07
     DEVELO
    -0.07
    рак
    -0.07
    ba
    -0.07
     Bundesliga
    -0.06
     eviction
    -0.06
     publish
    -0.06
    घ
    -0.06
     حض
    -0.06
    계
    -0.06
    POSITIVE LOGITS
     Outputs
    0.07
     crear
    0.06
    alore
    0.06
    Ｔ
    0.06
     porr
    0.06
     synonyms
    0.06
    (""));↵
    0.06
    ією
    0.06
    immune
    0.06
    ontrol
    0.06
    Act Density 0.005%

    No Known Activations