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

    Neuronpedia

    INDEX
    Explanations

    Unstructured varied content

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ass
    -0.07
    .route
    -0.07
     crossings
    -0.06
     distances
    -0.06
     Scrolls
    -0.06
    'es
    -0.06
     mistress
    -0.06
    .params
    -0.06
     ス
    -0.06
     Cater
    -0.06
    POSITIVE LOGITS
     объ
    0.07
     вдруг
    0.07
    象
    0.07
     maj
    0.07
    (heap
    0.07
    λίου
    0.07
    UILT
    0.06
     сказал
    0.06
     varsa
    0.06
    ael
    0.06
    Act Density 0.014%

    No Known Activations