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

    Neuronpedia

    INDEX
    Explanations

    OpenAI API

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     gi
    0.67
    Dsp
    0.65
    Strip
    0.60
    ेटा
    0.60
     conf
    0.60
     Bradshaw
    0.59
    Bounds
    0.59
     trav
    0.59
    メイク
    0.59
     roce
    0.59
    POSITIVE LOGITS
     OC
    1.07
     ओ
    1.03
     OA
    0.96
     ऑक्सी
    0.95
     ozone
    0.92
     SIINFEKL
    0.89
     OMX
    0.88
     oxide
    0.87
    ΠΟ
    0.82
     OE
    0.80
    Act Density 0.342%

    No Known Activations