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

    Neuronpedia

    INDEX
    Explanations

    by the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Racing
    0.51
     arma
    0.50
     intervene
    0.49
    㻐
    0.48
    騇
    0.48
    ំនួន
    0.46
    둴
    0.46
    枃
    0.46
    <
    0.45
    ૫
    0.45
    POSITIVE LOGITS
    t
    0.55
    in
    0.54
    tree
    0.53
    QI
    0.51
    ai
    0.51
    timetable
    0.51
    NRI
    0.51
    tä
    0.50
    TAU
    0.50
    tour
    0.50
    Act Density 0.000%

    No Known Activations