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

    Neuronpedia

    INDEX
    Explanations

    math and programming problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     prohibition
    -0.07
     Henrik
    -0.07
     Neutral
    -0.07
     rebel
    -0.07
     combat
    -0.06
     enh
    -0.06
    _gid
    -0.06
     wears
    -0.06
     Marxist
    -0.06
    Dialogue
    -0.06
    POSITIVE LOGITS
     }
↵
    0.08
     assorted
    0.07
     конс
    0.07
     documentation
    0.07
    .volley
    0.06
     samot
    0.06
    텔
    0.06
     StringWriter
    0.06
    /wiki
    0.06
    zyć
    0.06
    Act Density 0.081%

    No Known Activations