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

    Neuronpedia

    INDEX
    Explanations

    .entity or .model

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     강
    -0.07
     notified
    -0.07
    Liverpool
    -0.07
     groundbreaking
    -0.07
     regulators
    -0.07
     лей
    -0.07
    addtogroup
    -0.06
    setStatus
    -0.06
    "net
    -0.06
     Generator
    -0.06
    POSITIVE LOGITS
    ength
    0.06
     disg
    0.06
     alanda
    0.06
    ادل
    0.06
    -on
    0.06
    -xs
    0.06
     mnoho
    0.06
     солн
    0.06
     SETTINGS
    0.06
     Himal
    0.05
    Act Density 0.013%

    No Known Activations