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

    Neuronpedia

    INDEX
    Explanations

    matrices and equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     سید
    -0.07
    _element
    -0.06
     cafe
    -0.06
    .Address
    -0.06
    _frequency
    -0.06
    ={"/
    -0.06
     IReadOnly
    -0.06
    ывает
    -0.06
    hu
    -0.06
     review
    -0.06
    POSITIVE LOGITS
     Woo
    0.06
    ptive
    0.06
     ה
    0.06
     Rak
    0.06
    VEL
    0.06
    posal
    0.06
     wasted
    0.06
     SEN
    0.06
    Exclusive
    0.06
     democr
    0.06
    Act Density 0.032%

    No Known Activations