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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     disrupting
    -0.07
    .toggle
    -0.07
    anos
    -0.07
     converts
    -0.06
    	DECLARE
    -0.06
    ");
    -0.06
    eq
    -0.06
    -auth
    -0.06
     hiring
    -0.06
     daddy
    -0.06
    POSITIVE LOGITS
     ł
    0.07
     близ
    0.07
    Series
    0.07
    aqu
    0.06
    Codec
    0.06
    選
    0.06
    ただ
    0.06
    spd
    0.06
     myslí
    0.06
    lıyor
    0.06
    Act Density 0.029%

    No Known Activations