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

    Neuronpedia

    INDEX
    Explanations

    Confirming understanding/details

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .RightToLeft
    -0.07
    hh
    -0.06
     UW
    -0.06
    ])
↵
    -0.06
    İR
    -0.06
     `}↵
    -0.06
    Assembler
    -0.06
    Controls
    -0.06
    eggies
    -0.06
     backup
    -0.06
    POSITIVE LOGITS
     reconoc
    0.07
     españ
    0.06
     unnamed
    0.06
    clientId
    0.06
    .select
    0.06
     cooker
    0.06
     цій
    0.06
     candidate
    0.06
    _label
    0.06
     Excellent
    0.06
    Act Density 0.219%

    No Known Activations