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

    Neuronpedia

    INDEX
    Explanations

    explicitness and implicitness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     melan
    0.45
     Melanie
    0.44
     south
    0.43
     대
    0.43
    affe
    0.43
     melod
    0.43
     syd
    0.43
     greeted
    0.42
     glTranslatef
    0.42
    south
    0.41
    POSITIVE LOGITS
     Implicit
    0.70
     implicit
    0.70
    implicit
    0.69
     implic
    0.66
    Implicit
    0.64
    itness
    0.55
     implicate
    0.51
     implicitly
    0.50
    implicitly
    0.49
     implicated
    0.48
    Act Density 0.007%

    No Known Activations