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

    Neuronpedia

    INDEX
    Explanations

    In

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Destination
    -0.08
     Heads
    -0.07
    ��
    -0.07
    _NE
    -0.06
     Them
    -0.06
    Custom
    -0.06
     Return
    -0.06
     čas
    -0.06
     estos
    -0.06
     크
    -0.06
    POSITIVE LOGITS
    _sig
    0.07
     á
    0.06
    851
    0.06
    يكي
    0.06
     bardzo
    0.06
    257
    0.06
    習
    0.06
     gon
    0.06
    ウト
    0.06
     elders
    0.06
    Act Density 0.000%

    No Known Activations