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

    Neuronpedia

    INDEX
    Explanations

    volunteering and assisting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Heisenberg
    0.61
     algoritmo
    0.54
     pulsating
    0.53
     sofistic
    0.52
     $>
    0.52
     GeV
    0.52
     puiss
    0.51
    ローバル
    0.49
     orthogon
    0.49
     جوہری
    0.49
    POSITIVE LOGITS
     volunteering
    1.66
     volunteer
    1.61
     assisting
    1.58
     volunteered
    1.47
    协助
    1.45
    帮忙
    1.45
    volunteer
    1.44
     volunteers
    1.38
     Volunteer
    1.38
     helping
    1.36
    Act Density 0.372%

    No Known Activations