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

    Neuronpedia

    INDEX
    Explanations

    C++ memory management

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    gebracht
    -0.07
    gior
    -0.07
    Unified
    -0.07
     acordo
    -0.07
     Ап
    -0.07
     AP
    -0.07
    _HE
    -0.07
    획
    -0.07
     beginning
    -0.07
     BER
    -0.07
    POSITIVE LOGITS
    外
    0.09
     hostel
    0.08
     внеш
    0.08
     внешний
    0.08
     lưu
    0.08
     ग्राम
    0.08
     confiar
    0.08
     cottage
    0.08
     tempor
    0.08
     pagkatapos
    0.08
    Act Density 0.002%

    No Known Activations