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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     RECORD
    -0.07
     Αρ
    -0.07
     Cor
    -0.07
     rumor
    -0.06
    ;width
    -0.06
     Married
    -0.06
    知道
    -0.06
     им
    -0.06
    िय
    -0.06
     ear
    -0.06
    POSITIVE LOGITS
     odio
    0.07
    ydro
    0.06
    regn
    0.06
    /graphql
    0.06
     carbohydrates
    0.06
    арат
    0.06
    юсь
    0.06
    mrt
    0.06
    ambre
    0.06
     Birch
    0.06
    Act Density 0.000%

    No Known Activations