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

    Neuronpedia

    INDEX
    Explanations

    animal descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     кораб
    -0.07
    ख
    -0.06
    이라는
    -0.06
    ографія
    -0.06
    خ
    -0.06
    .loaded
    -0.06
    ์อ
    -0.06
     после
    -0.05
     Ч
    -0.05
     تصو
    -0.05
    POSITIVE LOGITS
     protective
    0.07
    73
    0.07
     idea
    0.06
     Protective
    0.06
     EM
    0.06
     Solic
    0.06
    Android
    0.06
    .Drawing
    0.06
     attack
    0.06
    PCI
    0.06
    Act Density 0.023%

    No Known Activations