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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .employee
    -0.06
    Liquid
    -0.06
     inspiring
    -0.06
    bcm
    -0.06
     confuse
    -0.06
    .ToShort
    -0.06
     earrings
    -0.06
     up
    -0.06
    _attachment
    -0.06
    "/>.↵
    -0.06
    POSITIVE LOGITS
     wrath
    0.07
    _Insert
    0.06
    ส
    0.06
    ünd
    0.06
    )/(
    0.06
    режд
    0.06
    bet
    0.06
    βέρ
    0.06
     bets
    0.06
    ğu
    0.06
    Act Density 0.002%

    No Known Activations