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

    Neuronpedia

    INDEX
    Explanations

    story

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     distraction
    -0.07
     honor
    -0.07
     requestData
    -0.07
    _limit
    -0.07
     dislike
    -0.06
     gather
    -0.06
    lasyon
    -0.06
    爵
    -0.06
    cohol
    -0.06
     skl
    -0.06
    POSITIVE LOGITS
     story
    0.10
     Story
    0.08
     STORY
    0.07
    -story
    0.07
    Segments
    0.06
    /story
    0.06
    맥
    0.06
     điển
    0.06
    导
    0.06
     secrets
    0.06
    Act Density 0.027%

    No Known Activations