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

    Neuronpedia

    INDEX
    Explanations

    code or data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    анти
    -0.07
    onomy
    -0.07
     prend
    -0.06
    ayet
    -0.06
    Cross
    -0.06
    ılığıyla
    -0.06
    asz
    -0.06
    acho
    -0.06
     blogging
    -0.06
    .Unsupported
    -0.06
    POSITIVE LOGITS
     Poss
    0.06
     #
↵
    0.06
     Л
    0.06
    〕
    0.06
    ної
    0.06
     встанов
    0.06
    pak
    0.06
     Feb
    0.06
     creditors
    0.06
    уватися
    0.06
    Act Density 0.071%

    No Known Activations