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

    Neuronpedia

    INDEX
    Explanations

    have, need, want

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Be
    1.16
     Be
    1.12
     باشد
    0.85
    be
    0.81
    BE
    0.75
     aient
    0.73
    unable
    0.68
    了不少
    0.68
     soient
    0.67
     puissent
    0.67
    POSITIVE LOGITS
     belong
    1.27
     want
    1.21
     have
    1.19
     seem
    1.17
     resemble
    1.16
     deserve
    1.15
     need
    1.14
     owe
    1.11
     know
    1.10
     require
    1.08
    Act Density 0.217%

    No Known Activations