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

    Neuronpedia

    INDEX
    Explanations

    using

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    "/
    -0.06
     Macedonia
    -0.06
     अत
    -0.06
    力的
    -0.06
     د
    -0.06
     кня
    -0.06
     ant
    -0.06
    到的
    -0.06
     lamps
    -0.06
    尚
    -0.06
    POSITIVE LOGITS
    uggle
    0.07
    som
    0.07
    leads
    0.07
     good
    0.06
    lili
    0.06
     remin
    0.06
    .Margin
    0.06
     vide
    0.06
    ($)
    0.06
    ivil
    0.06
    Act Density 0.001%

    No Known Activations