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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    톡
    -0.08
    _owner
    -0.07
     безоп
    -0.07
    𫘬
    -0.07
    inel
    -0.06
    鱽
    -0.06
    כלל
    -0.06
     düz
    -0.06
    桃
    -0.06
    otlin
    -0.06
    POSITIVE LOGITS
     editar
    0.09
     roofing
    0.08
    源于
    0.07
     divisible
    0.07
     Gilbert
    0.07
    報導
    0.06
     sulfate
    0.06
     kilometres
    0.06
     Maher
    0.06
    (infile
    0.06
    Act Density 0.003%

    No Known Activations