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

    Neuronpedia

    INDEX
    Explanations

    what

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     venue
    -0.07
     `_
    -0.07
    .deltaTime
    -0.07
    ิยม
    -0.07
    ंडल
    -0.06
    rak
    -0.06
    ّر
    -0.06
    ยาย
    -0.06
    InputElement
    -0.06
     PDF
    -0.06
    POSITIVE LOGITS
    ISED
    0.07
    wechat
    0.07
    statistics
    0.07
     keyword
    0.07
     temperature
    0.07
     educated
    0.06
     randomized
    0.06
    idak
    0.06
    amy
    0.06
     exclusion
    0.06
    Act Density 0.000%

    No Known Activations