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

    Neuronpedia

    INDEX
    Explanations

    pattern

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    θμ
    -0.07
    Enough
    -0.07
     chains
    -0.07
    lte
    -0.07
     cloth
    -0.06
     polic
    -0.06
     craftsmanship
    -0.06
     challenged
    -0.06
    _exp
    -0.06
    ํ
    -0.06
    POSITIVE LOGITS
    šek
    0.06
    _expiry
    0.06
     vo
    0.06
    ¨
    0.06
    ρ
    0.06
     Disney
    0.06
     досить
    0.06
    paragus
    0.06
    ρα
    0.06
     SELECT
    0.06
    Act Density 0.057%

    No Known Activations