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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     concluded
    -0.06
    itivity
    -0.06
     automobiles
    -0.06
    сен
    -0.06
    inema
    -0.06
     نیر
    -0.06
    OPSIS
    -0.06
     Cinema
    -0.06
    -memory
    -0.06
    achine
    -0.06
    POSITIVE LOGITS
    했던
    0.07
    .userInteractionEnabled
    0.07
     scanf
    0.07
    _fx
    0.07
     hogy
    0.06
     gv
    0.06
     Xuân
    0.06
    〃
    0.06
    vant
    0.06
    می
    0.06
    Act Density 0.020%

    No Known Activations