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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    lst
    -0.07
    리고
    -0.07
    -ar
    -0.06
     jogging
    -0.06
     Bou
    -0.06
     Kết
    -0.06
     вместе
    -0.06
    _AR
    -0.06
    enda
    -0.06
    بيرة
    -0.06
    POSITIVE LOGITS
    '))↵
    0.07
     );↵↵
    0.06
     ''
    0.06
     drill
    0.06
     insets
    0.06
    !")↵↵
    0.06
    trait
    0.06
     vọng
    0.06
    Flag
    0.06
     pours
    0.06
    Act Density 0.003%

    No Known Activations