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

    Neuronpedia

    INDEX
    Explanations

    scientific citations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    см
    -0.07
     chess
    -0.07
     Arbit
    -0.06
    .fil
    -0.06
     Brotherhood
    -0.06
    _NUMBER
    -0.06
     shaken
    -0.06
     MLS
    -0.06
    _LITERAL
    -0.06
    trimmed
    -0.06
    POSITIVE LOGITS
    lications
    0.07
     Disneyland
    0.07
     thankfully
    0.07
     Gates
    0.06
     안전
    0.06
    ':↵↵
    0.06
     공동
    0.06
    (bp
    0.06
     pinterest
    0.06
     Churches
    0.06
    Act Density 0.006%

    No Known Activations