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

    Neuronpedia

    INDEX
    Explanations

    Mathematics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    αν
    -0.07
    銀行
    -0.07
    [state
    -0.07
    (Request
    -0.07
    ongoose
    -0.06
    [selected
    -0.06
    iji
    -0.06
     จาก
    -0.06
     CALLBACK
    -0.06
    jav
    -0.06
    POSITIVE LOGITS
     poking
    0.07
    Sup
    0.06
    .destroyAllWindows
    0.06
     buck
    0.06
     लड
    0.06
    Oct
    0.06
    vf
    0.06
     Fusion
    0.06
     помещ
    0.05
     homeowners
    0.05
    Act Density 0.008%

    No Known Activations