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

    Neuronpedia

    INDEX
    Explanations

    mathematical notation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     YES
    -0.07
    即
    -0.06
    ICIAL
    -0.06
    ันย
    -0.06
     Recipes
    -0.06
     Tuesday
    -0.06
    "><
    -0.06
    шли
    -0.06
     ucwords
    -0.06
    _clear
    -0.06
    POSITIVE LOGITS
    .SerializeObject
    0.06
    電話
    0.06
     markup
    0.06
    خصص
    0.06
    užel
    0.06
    istrovství
    0.06
    erokee
    0.06
    _radi
    0.06
    فل
    0.05
    σης
    0.05
    Act Density 0.025%

    No Known Activations