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

    Neuronpedia

    INDEX
    Explanations

    by verb-ing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     an
    0.52
    ل
    0.51
     a
    0.51
     strikeouts
    0.51
     inferences
    0.50
     brightness
    0.50
     the
    0.49
    ৮
    0.49
     hangers
    0.48
     jugement
    0.48
    POSITIVE LOGITS
     providing
    0.58
     allowing
    0.54
    allowing
    0.47
    Providing
    0.46
     offering
    0.45
    ux
    0.45
    arris
    0.44
     creating
    0.44
     choosing
    0.43
    ebut
    0.43
    Act Density 0.021%

    No Known Activations