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

    Neuronpedia

    INDEX
    Explanations

    coding involving time

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     chaud
    -0.07
    éducation
    -0.07
    Soup
    -0.07
    首富
    -0.07
    bcd
    -0.07
     birthday
    -0.07
     wc
    -0.07
    噴
    -0.07
    结构性
    -0.06
    rst
    -0.06
    POSITIVE LOGITS
     Violence
    0.08
     Instance
    0.08
    为一体
    0.07
    :[
    0.07
    ervice
    0.07
    _SESSION
    0.07
    <Event
    0.07
    (v
    0.07
    _LOG
    0.07
     amassed
    0.07
    Act Density 0.001%

    No Known Activations