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

    Neuronpedia

    INDEX
    Explanations

    scale

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mountains
    -0.06
     STATE
    -0.06
    ificent
    -0.06
     标
    -0.06
     thông
    -0.06
     мног
    -0.06
     funct
    -0.06
    рук
    -0.06
    ###############################################################################↵
    -0.06
     State
    -0.06
    POSITIVE LOGITS
    addAction
    0.07
    -eff
    0.07
    IntervalSince
    0.07
     Επ
    0.06
    ())){↵
    0.06
     Sized
    0.06
     центра
    0.06
    _Integer
    0.06
    丁
    0.06
    steel
    0.06
    Act Density 0.007%

    No Known Activations