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

    Neuronpedia

    INDEX
    Explanations

    other

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     (
    -0.09
     combined
    -0.08
    '
    -0.08
    2
    -0.08
    .↵↵
    -0.08
     appropriate
    -0.08
     .
    -0.07
     base
    -0.07
     digits
    -0.07
     structure
    -0.07
    POSITIVE LOGITS
     Alternatives
    0.13
     alternativas
    0.12
     alternatives
    0.12
     zusätzliche
    0.12
     alternatif
    0.11
     альтернатив
    0.11
    alternative
    0.11
     batzuk
    0.11
     дополнительные
    0.11
     سایر
    0.11
    Act Density 0.074%

    No Known Activations