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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	let
    -0.08
    .card
    -0.07
    _confirm
    -0.07
    Judge
    -0.07
    .PerformLayout
    -0.07
     Lamp
    -0.07
    .ch
    -0.06
    berman
    -0.06
    -0.06
     searches
    -0.06
    POSITIVE LOGITS
    προ
    0.06
    ność
    0.06
    _DAC
    0.06
     informatie
    0.06
     prázd
    0.06
    (desc
    0.06
    MITTED
    0.06
    ندي
    0.06
     Kuala
    0.06
     tangible
    0.06
    Act Density 0.057%

    No Known Activations