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

    Neuronpedia

    INDEX
    Explanations

    Rewording/Paraphrasing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ornament
    -0.06
    -house
    -0.06
     lids
    -0.06
    ibase
    -0.06
    vez
    -0.06
     глу
    -0.06
    gle
    -0.06
    Includes
    -0.06
    ليم
    -0.06
     palette
    -0.06
    POSITIVE LOGITS
     Security
    0.08
    "log
    0.07
     перед
    0.07
    _finished
    0.06
     Cust
    0.06
    ,status
    0.06
    getNode
    0.06
    kaç
    0.06
     پایین
    0.06
     guardar
    0.06
    Act Density 0.008%

    No Known Activations