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
    −
    -0.07
    FFFFFFFF
    -0.06
    .Marker
    -0.06
     싶
    -0.06
    ecycle
    -0.06
     khăn
    -0.06
    �
    -0.06
    uyla
    -0.06
     lehet
    -0.06
    ्गत
    -0.06
    POSITIVE LOGITS
    	options
    0.08
    ันท
    0.06
    ΙΤ
    0.06
    _embedding
    0.06
     auditory
    0.06
     fisheries
    0.06
    ượt
    0.06
    .cart
    0.06
    coming
    0.06
     Modifier
    0.06
    Act Density 0.018%

    No Known Activations