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

    Neuronpedia

    INDEX
    Explanations

    outlines chapters and sections

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     conjugates
    0.44
     codon
    0.42
     근무
    0.42
     pair
    0.42
     elastomer
    0.40
     rotation
    0.39
    組み合わせ
    0.39
     Simulator
    0.39
     beliefs
    0.39
     tweezers
    0.39
    POSITIVE LOGITS
    Outline
    1.16
     Outline
    1.13
     outline
    1.08
     headings
    1.02
     outlines
    0.97
    outline
    0.97
    headings
    0.93
     chapters
    0.88
     outlining
    0.88
    章节
    0.86
    Act Density 0.016%

    No Known Activations