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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _HAS
    -0.07
     dwell
    -0.06
    최신
    -0.06
    _MEM
    -0.06
     Charger
    -0.06
     cười
    -0.06
    _Enc
    -0.06
    خص
    -0.06
    UGC
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     bowling
    0.07
    BO
    0.07
     sto
    0.07
     (;;)
    0.07
    .lista
    0.07
    #aa
    0.06
    prene
    0.06
     ***/↵
    0.06
     boards
    0.06
     damping
    0.06
    Act Density 0.002%

    No Known Activations