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

    Neuronpedia

    INDEX
    Explanations

    ais

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ูช
    -0.07
    candidates
    -0.07
     симв
    -0.06
    rain
    -0.06
     kế
    -0.06
     dominated
    -0.06
     Leonard
    -0.06
    остей
    -0.06
    _inches
    -0.06
    .Shapes
    -0.06
    POSITIVE LOGITS
     preferable
    0.06
     frem
    0.06
    Isl
    0.06
     aforementioned
    0.06
     dreadful
    0.06
     ček
    0.06
    (best
    0.06
     (...
    0.06
    	open
    0.06
     listen
    0.06
    Act Density 0.059%

    No Known Activations