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

    Neuronpedia

    INDEX
    Explanations

    philosophical books and love

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     �
    -0.09
     vérifier
    -0.09
    	Logger
    -0.09
    urada
    -0.09
    anfan
    -0.09
    айл
    -0.09
    ویه
    -0.08
     առողջ
    -0.08
     проверить
    -0.08
     өдөр
    -0.08
    POSITIVE LOGITS
     liqu
    0.07
    _ready
    0.07
     abil
    0.07
     adhesive
    0.07
     dg
    0.07
     req
    0.07
     ture
    0.07
    ，包括
    0.07
     \(
    0.07
     druge
    0.07
    Act Density 0.001%

    No Known Activations