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

    Neuronpedia

    INDEX
    Explanations

    from

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ej
    -0.07
     gm
    -0.07
    Neighbors
    -0.06
    erved
    -0.06
     qs
    -0.06
    .setCurrent
    -0.06
     rentals
    -0.06
    ors
    -0.06
    .sk
    -0.06
     výsled
    -0.06
    POSITIVE LOGITS
    480
    0.06
    ΙΛ
    0.06
    ınız
    0.06
    asaki
    0.06
    Accessible
    0.06
     violently
    0.06
     amongst
    0.06
    탈
    0.06
    论坛
    0.06
     usur
    0.06
    Act Density 0.020%

    No Known Activations