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

    Neuronpedia

    INDEX
    Explanations

    AR-15

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     neuen
    -0.07
     ds
    -0.07
    ав
    -0.07
     수
    -0.07
    aca
    -0.07
    ULE
    -0.07
    蘇
    -0.06
    ule
    -0.06
    交
    -0.06
    нач
    -0.06
    POSITIVE LOGITS
    )value
    0.07
    -sizing
    0.07
    equip
    0.07
    ']))↵↵
    0.06
    _MetadataUsageId
    0.06
    _IList
    0.06
     beauty
    0.06
    ",
↵
    0.06
     statuses
    0.06
     disturbed
    0.06
    Act Density 0.005%

    No Known Activations