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

    Neuronpedia

    INDEX
    Explanations

    Legal case context

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    名前
    -0.06
    |x
    -0.06
    芳
    -0.06
    桐
    -0.06
    LEX
    -0.06
     quer
    -0.06
     comunidad
    -0.06
    todos
    -0.06
     rev
    -0.06
    radouro
    -0.05
    POSITIVE LOGITS
    .trigger
    0.07
    对于
    0.07
    	parameters
    0.06
    PEND
    0.06
    _Function
    0.06
     genius
    0.06
    _MY
    0.06
     حف
    0.06
    ('|
    0.06
    [...,
    0.06
    Act Density 0.033%

    No Known Activations