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

    Neuronpedia

    INDEX
    Explanations

    press releases and announcements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     superposition
    0.49
     tanh
    0.49
     ถ้า
    0.47
     polynomials
    0.46
     sklearn
    0.46
     trainable
    0.46
     mutable
    0.46
     tensors
    0.45
     groupBox
    0.45
     humoral
    0.44
    POSITIVE LOGITS
     Announces
    0.80
     announces
    0.73
    newswire
    0.68
    Newswire
    0.68
    PRNewswire
    0.67
    prnewswire
    0.66
     пресс
    0.65
     announcement
    0.64
     anunció
    0.63
    press
    0.62
    Act Density 0.010%

    No Known Activations