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

    Neuronpedia

    INDEX
    Explanations

    source code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _binary
    -0.06
    100
    -0.06
     Boulevard
    -0.06
     dangerous
    -0.06
     TRE
    -0.06
     PhD
    -0.06
    .offsetWidth
    -0.06
     Natural
    -0.06
     LEFT
    -0.06
     magazines
    -0.06
    POSITIVE LOGITS
    /disc
    0.07
    ísk
    0.07
     cadre
    0.07
     名無し
    0.07
    出了
    0.07
    PTION
    0.06
    mıyor
    0.06
    <Tuple
    0.06
    orum
    0.06
     burge
    0.06
    Act Density 0.055%

    No Known Activations