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

    Neuronpedia

    INDEX
    Explanations

    absurd, curious, disability

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     proficiency
    0.44
     eğ
    0.41
     окна
    0.39
    DropDownItem
    0.38
     inapplicable
    0.38
    मेट्री
    0.38
     Elevator
    0.38
     Applicable
    0.37
    devkit
    0.37
     погру
    0.37
    POSITIVE LOGITS
     quad
    0.43
     Quad
    0.41
     softball
    0.41
     poissons
    0.40
    getList
    0.40
     बाइक्स
    0.39
    QUADS
    0.39
    Quad
    0.38
     Kobayashi
    0.37
    Kob
    0.37
    Act Density 0.000%

    No Known Activations