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

    Neuronpedia

    INDEX
    Explanations

    citations in scientific papers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    остей
    -0.07
     tiles
    -0.06
    え
    -0.06
    HttpStatus
    -0.06
    лены
    -0.06
     Figures
    -0.06
    province
    -0.06
     світ
    -0.06
    anter
    -0.06
    児
    -0.06
    POSITIVE LOGITS
    Constraints
    0.07
    .Mutex
    0.07
    uele
    0.07
     لدي
    0.06
     wes
    0.06
     flawed
    0.06
    ++){↵
    0.06
    ,state
    0.06
    ++){↵↵
    0.06
    ,const
    0.06
    Act Density 0.014%

    No Known Activations