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

    Neuronpedia

    INDEX
    Explanations

    filter

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ump
    -0.07
    Performance
    -0.07
    ただ
    -0.06
     Ngày
    -0.06
     따라
    -0.06
    ıyor
    -0.06
    幼
    -0.06
    �
    -0.06
    UMP
    -0.06
     MOZ
    -0.06
    POSITIVE LOGITS
    -dimensional
    0.06
    ........................
    0.06
     liquids
    0.06
    _filled
    0.06
     turbulent
    0.06
     koje
    0.06
     gravitational
    0.06
     Мал
    0.06
     infect
    0.06
     locals
    0.06
    Act Density 0.007%

    No Known Activations