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

    Neuronpedia

    INDEX
    Explanations

    name

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cops
    -0.07
     reinforced
    -0.07
     southern
    -0.07
    итися
    -0.07
     upper
    -0.06
    Against
    -0.06
    Animated
    -0.06
    Numero
    -0.06
     قیمت
    -0.06
     shrinking
    -0.06
    POSITIVE LOGITS
     роботу
    0.08
    CT
    0.06
    ambah
    0.06
     توضی
    0.06
    obbies
    0.06
    립
    0.06
     واس
    0.06
    _Display
    0.06
    lad
    0.06
    ét
    0.06
    Act Density 0.061%

    No Known Activations