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

    Neuronpedia

    INDEX
    Explanations

    I

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     recursively
    -0.09
     exploration
    -0.08
     मिलने
    -0.07
     Australians
    -0.07
     transcription
    -0.07
     barrier
    -0.07
     GMT
    -0.07
     explore
    -0.07
     explored
    -0.07
     dynamically
    -0.07
    POSITIVE LOGITS
     vielmehr
    0.09
     অভিযোগ
    0.09
    一句
    0.09
     표현
    0.09
    句话
    0.09
     wording
    0.09
    句
    0.09
     accusing
    0.09
    Rather
    0.08
     ಹೇಳ
    0.08
    Act Density 0.005%

    No Known Activations