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

    Neuronpedia

    INDEX
    Explanations

    fiction

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Mahmoud
    -0.08
    ix
    -0.07
    Alchemy
    -0.07
    GH
    -0.07
     prefixed
    -0.06
     八
    -0.06
    _vectors
    -0.06
    ……↵↵
    -0.06
     burn
    -0.06
     languages
    -0.06
    POSITIVE LOGITS
     elim
    0.06
     thuộc
    0.06
     scraps
    0.06
     hmot
    0.05
     ";"
    0.05
    charted
    0.05
    edm
    0.05
    *[
    0.05
    .case
    0.05
    >m
    0.05
    Act Density 0.059%

    No Known Activations