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

    Neuronpedia

    INDEX
    Explanations

    "with the help of"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     "`
    -0.08
     phố
    -0.06
     mensaje
    -0.06
    Rotate
    -0.06
    Declaration
    -0.06
    意见
    -0.06
    Race
    -0.06
    initWith
    -0.06
     Tipo
    -0.05
    SOLE
    -0.05
    POSITIVE LOGITS
    _interp
    0.08
     приготов
    0.07
     lingerie
    0.06
     знов
    0.06
    ượng
    0.06
    _forms
    0.06
     активно
    0.06
     còn
    0.06
     вироб
    0.06
     процед
    0.06
    Act Density 0.025%

    No Known Activations