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

    Neuronpedia

    INDEX
    Explanations

    Questions, abilities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     parametro
    -0.07
     CAR
    -0.06
     ﾄ
    -0.06
    PV
    -0.06
     undefeated
    -0.06
     ETA
    -0.06
    rá
    -0.06
    िद
    -0.06
     Arc
    -0.06
     kolej
    -0.06
    POSITIVE LOGITS
    (grammar
    0.07
    (height
    0.07
    خص
    0.07
    .duration
    0.07
    (gt
    0.07
    .…
    0.07
     nuest
    0.06
    TagName
    0.06
    fieldname
    0.06
     خرد
    0.06
    Act Density 0.078%

    No Known Activations