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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Therefore
    -0.07
    -yard
    -0.06
    .medium
    -0.06
    Exclusive
    -0.06
    FORE
    -0.06
    ділу
    -0.06
     полез
    -0.06
    μβρίου
    -0.06
     چهار
    -0.06
    อำนวย
    -0.06
    POSITIVE LOGITS
    	constexpr
    0.07
     (${
    0.07
     getConnection
    0.07
     ´
    0.06
    -${
    0.06
    .xticks
    0.06
    classifier
    0.06
     prem
    0.06
     TableRow
    0.06
    ][:
    0.06
    Act Density 0.016%

    No Known Activations