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

    Neuronpedia

    INDEX
    Explanations

    Formal/technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _EDEFAULT
    -0.06
     FormControl
    -0.06
     فور
    -0.06
    ，又
    -0.06
    스티
    -0.06
     نص
    -0.06
     welfare
    -0.06
    τικα
    -0.06
     파일첨부
    -0.06
     anomalies
    -0.06
    POSITIVE LOGITS
     fasting
    0.07
     Stanford
    0.07
     싸
    0.06
     شناس
    0.06
     mistaken
    0.06
    undreds
    0.06
     foss
    0.06
     шк
    0.06
     depending
    0.06
    hydrate
    0.06
    Act Density 0.000%

    No Known Activations