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

    Neuronpedia

    INDEX
    Explanations

    2

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    >',
    -0.06
     sido
    -0.06
     Dur
    -0.06
     posing
    -0.06
     Merch
    -0.06
     h
    -0.06
    	reg
    -0.06
     Clock
    -0.06
    Detroit
    -0.06
    -expression
    -0.06
    POSITIVE LOGITS
    .Virtual
    0.08
    9
    0.07
    ило
    0.06
     Chancellor
    0.06
    ARE
    0.06
    (aa
    0.06
    .opens
    0.06
     취
    0.06
    2
    0.06
    utilus
    0.06
    Act Density 0.004%

    No Known Activations