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

    Neuronpedia

    INDEX
    Explanations

    timestamps

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    539
    -0.07
    	task
    -0.07
    وک
    -0.07
    ót
    -0.07
     Party
    -0.07
    ostí
    -0.06
    7
    -0.06
    )y
    -0.06
    (work
    -0.06
    elems
    -0.06
    POSITIVE LOGITS
    SSERT
    0.06
     чист
    0.06
    /select
    0.06
    ाहत
    0.06
    -percent
    0.06
    ılım
    0.06
     마지막
    0.06
    chedulers
    0.06
    .WebControls
    0.06
    Instructions
    0.06
    Act Density 0.003%

    No Known Activations