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

    Neuronpedia

    INDEX
    Explanations

    #endif

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    cor
    -0.07
     Mim
    -0.07
    (indices
    -0.07
     embodiments
    -0.07
    .prod
    -0.07
     RELATED
    -0.06
    游览
    -0.06
     rus
    -0.06
     perish
    -0.06
    top
    -0.06
    POSITIVE LOGITS
     massively
    0.07
     легко
    0.07
    noinspection
    0.07
    _raise
    0.07
    代表着
    0.07
     đứa
    0.07
    .readAs
    0.06
    攻坚战
    0.06
     hogy
    0.06
    批量
    0.06
    Act Density 0.000%

    No Known Activations