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

    Neuronpedia

    INDEX
    Explanations

    Parenthesis/apostrophes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     freezes
    -0.07
     realloc
    -0.07
    -notification
    -0.07
    (matches
    -0.07
    Sibling
    -0.07
    .SQLite
    -0.07
    眾
    -0.07
    edi
    -0.07
    飒
    -0.07
    פרופיל
    -0.07
    POSITIVE LOGITS
    写作
    0.07
     Zurich
    0.07
    lord
    0.07
     ',↵
    0.07
     Derby
    0.07
    apgolly
    0.07
    🦊
    0.06
     song
    0.06
    🕸
    0.06
    世界观
    0.06
    Act Density 0.025%

    No Known Activations