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

    Neuronpedia

    INDEX
    Explanations

    code/configuration

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    269
    -0.07
    ансов
    -0.07
    568
    -0.06
    _DIM
    -0.06
    _args
    -0.06
    970
    -0.06
    hur
    -0.06
    those
    -0.06
    004
    -0.06
    -Length
    -0.06
    POSITIVE LOGITS
     creampie
    0.07
     обуч
    0.07
    .pageX
    0.06
     Kod
    0.06
     Pole
    0.06
     прем
    0.06
    ABEL
    0.06
     explosives
    0.06
    این
    0.06
     sach
    0.06
    Act Density 0.290%

    No Known Activations