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

    Neuronpedia

    INDEX
    Explanations

    words starting with Man

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ال
    0.46
    Most
    0.45
     ஜீ
    0.45
    golang
    0.42
    지에
    0.41
     maliciously
    0.41
    mon
    0.40
    most
    0.40
    relsen
    0.39
     பட
    0.39
    POSITIVE LOGITS
    hattan
    0.68
     MAN
    0.66
     Man
    0.63
     マン
    0.62
     Manit
    0.56
    끽
    0.54
    Man
    0.51
     ম্যান
    0.51
     manipulator
    0.49
     ман
    0.49
    Act Density 0.033%

    No Known Activations