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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _skill
    -0.07
    gam
    -0.07
     Серед
    -0.07
     commence
    -0.07
    .java
    -0.06
     MMC
    -0.06
     tritur
    -0.06
     Pierce
    -0.06
     cuk
    -0.06
     Grim
    -0.06
    POSITIVE LOGITS
     Συ
    0.07
    ="'
    0.07
    belongsTo
    0.06
    /person
    0.06
     τη
    0.06
     arşivlendi
    0.06
     ninh
    0.06
    setStatus
    0.06
     Rookie
    0.06
     quarterback
    0.06
    Act Density 0.016%

    No Known Activations