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

    Neuronpedia

    INDEX
    Explanations

    foreign languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    iculos
    -0.07
    Cou
    -0.07
     tire
    -0.06
    omething
    -0.06
    _representation
    -0.06
    ête
    -0.06
    Re
    -0.06
    lug
    -0.06
    Gen
    -0.06
     kelim
    -0.06
    POSITIVE LOGITS
     FStar
    0.07
     mohli
    0.07
    _RAD
    0.07
    juries
    0.06
     lineman
    0.06
     ='
    0.06
    having
    0.06
    _filepath
    0.06
     divisible
    0.06
     Eğer
    0.06
    Act Density 0.189%

    No Known Activations