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

    Neuronpedia

    INDEX
    Explanations

    >

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    accumulator
    -0.08
    Integral
    -0.08
    קוס
    -0.07
    Decoration
    -0.07
    uj
    -0.07
    رياضي
    -0.07
     bastante
    -0.07
    打通
    -0.07
     Graphic
    -0.07
    dataType
    -0.07
    POSITIVE LOGITS
     Yö
    0.07
    .Un
    0.07
     ia
    0.07
     tweaks
    0.07
     Orchard
    0.06
    (:
    0.06
     رس
    0.06
     é
    0.06
    治愈
    0.06
    ."'
    0.06
    Act Density 0.000%

    No Known Activations