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

    Neuronpedia

    INDEX
    Explanations

    noun followed by "that" or identifier

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    有哪些
    0.54
     ہوجائیں
    0.46
    navbarNav
    0.44
     있도록
    0.44
     있지만
    0.44
     olabilir
    0.44
    以便
    0.44
     possam
    0.43
    ktions
    0.40
     cuales
    0.40
    POSITIVE LOGITS
     everyone
    0.89
     closest
    0.85
     everybody
    0.82
     nearest
    0.80
     responsible
    0.77
    everyone
    0.69
    closest
    0.66
     farthest
    0.66
     наиболее
    0.65
     الجميع
    0.65
    Act Density 0.029%

    No Known Activations