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

    Neuronpedia

    INDEX
    Explanations

    computer programs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    灵
    -0.07
     sto
    -0.06
    isa
    -0.06
    겨
    -0.06
    興
    -0.06
    [rand
    -0.06
     �
    -0.06
    ;width
    -0.06
    Sweet
    -0.06
    학회
    -0.06
    POSITIVE LOGITS
    imetype
    0.07
     upgraded
    0.07
    (groups
    0.07
    ется
    0.06
    _MPI
    0.06
    LAG
    0.06
     включ
    0.06
    hawks
    0.06
     suma
    0.06
     сбор
    0.06
    Act Density 0.000%

    No Known Activations