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

    Neuronpedia

    INDEX
    Explanations

    Research papers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     learns
    -0.06
     brands
    -0.06
    ゲーム
    -0.06
    행
    -0.06
                                        ↵
    -0.06
    已
    -0.06
    _width
    -0.06
    np
    -0.06
     licences
    -0.06
     physics
    -0.06
    POSITIVE LOGITS
     Afr
    0.07
     Naruto
    0.06
    UTO
    0.06
     semif
    0.06
    McC
    0.06
    Hola
    0.06
    caption
    0.06
     Investments
    0.06
     області
    0.06
    uto
    0.06
    Act Density 0.023%

    No Known Activations