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

    Neuronpedia

    INDEX
    Explanations

    Once

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ила
    -0.07
     Digit
    -0.07
    ности
    -0.06
     τους
    -0.06
     ，
    -0.06
    .constraint
    -0.06
    ρού
    -0.06
    Spe
    -0.06
     Features
    -0.06
    κυ
    -0.06
    POSITIVE LOGITS
    webElement
    0.08
     Mehmet
    0.07
     Oven
    0.07
    .Publish
    0.07
     웹
    0.07
    )["
    0.06
    macen
    0.06
     หม
    0.06
    (us
    0.06
     дает
    0.06
    Act Density 0.012%

    No Known Activations