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

    Neuronpedia

    INDEX
    Explanations

    once

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ,tp
    -0.08
     스스
    -0.07
     TOD
    -0.07
    守
    -0.07
    ТО
    -0.07
    raising
    -0.07
     Mam
    -0.06
     bottle
    -0.06
     TOP
    -0.06
     Saf
    -0.06
    POSITIVE LOGITS
    ณ
    0.07
    0.07
    gradient
    0.07
    formula
    0.06
    ogram
    0.06
     Posted
    0.06
    PROGRAM
    0.06
    苏州市
    0.06
    글
    0.06
     فيما
    0.06
    Act Density 0.011%

    No Known Activations