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

    Neuronpedia

    INDEX
    Explanations

    math problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ophon
    -0.07
     coef
    -0.06
    Peace
    -0.06
    ับการ
    -0.06
    Window
    -0.06
     pData
    -0.06
     정부
    -0.06
     [{'
    -0.06
    nutím
    -0.06
     eos
    -0.06
    POSITIVE LOGITS
     ABS
    0.06
     athlete
    0.06
     garnered
    0.06
     surpass
    0.06
    .Stage
    0.06
    ,V
    0.06
    jà
    0.06
    懂
    0.06
    stalk
    0.06
     bpp
    0.06
    Act Density 0.013%

    No Known Activations