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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mActivity
    -0.07
    usuarios
    -0.06
    _por
    -0.06
    لعاب
    -0.06
    CONF
    -0.06
     Algorithms
    -0.06
    Than
    -0.06
     ruining
    -0.06
    bbing
    -0.06
    .payment
    -0.06
    POSITIVE LOGITS
     mon
    0.06
     Revenge
    0.06
    ]")↵
    0.06
     ﺍ
    0.06
     的
    0.06
     stě
    0.06
     simpler
    0.06
     Episodes
    0.06
    .itemId
    0.06
    _RANDOM
    0.06
    Act Density 0.001%

    No Known Activations