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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    //----------------------------------------------------------------------------------------------------------------
    -0.07
     ま
    -0.06
    ンピ
    -0.06
     popul
    -0.06
    鐵
    -0.06
     flavorful
    -0.06
    الف
    -0.06
    ขาย
    -0.06
    /tos
    -0.06
    addPreferredGap
    -0.06
    POSITIVE LOGITS
    PX
    0.07
     与
    0.07
     Therm
    0.06
    Duration
    0.06
     Sierra
    0.06
    maxLength
    0.06
     suitability
    0.06
    Scr
    0.06
    Snap
    0.06
     Mom
    0.06
    Act Density 0.000%

    No Known Activations