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

    Neuronpedia

    INDEX
    Explanations

    text inside curly brackets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    usin
    0.50
    nero
    0.50
    igere
    0.49
    떳
    0.48
    atay
    0.47
    แค
    0.46
    ('.')
    0.45
    eh
    0.44
    㬶
    0.44
    usakan
    0.44
    POSITIVE LOGITS
     can
    0.52
     Components
    0.50
     Tensor
    0.49
     niezwy
    0.47
     Wear
    0.46
     COMPONENTS
    0.46
     mammary
    0.45
     components
    0.44
     Speakers
    0.44
     tenfold
    0.44
    Act Density 0.000%

    No Known Activations