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

    Neuronpedia

    INDEX
    Explanations

    IT/JIT

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     WELL
    -0.07
     spanking
    -0.06
    oldem
    -0.06
     currentValue
    -0.06
     pasado
    -0.06
    퍽
    -0.06
    utowired
    -0.06
    ecast
    -0.06
    �
    -0.06
    fern
    -0.06
    POSITIVE LOGITS
     relevance
    0.08
     Rapid
    0.07
     Ethics
    0.07
     timed
    0.07
    ตร
    0.07
    itated
    0.07
    اعة
    0.07
    merchant
    0.07
     uom
    0.07
     יצירת
    0.07
    Act Density 0.001%

    No Known Activations