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

    Neuronpedia

    INDEX
    Explanations

    all [adjective/noun]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    B
    0.64
     orice
    0.58
     varje
    0.57
    drug
    0.55
     ಯಾವುದೇ
    0.55
     любые
    0.55
     není
    0.54
     যেকোন
    0.54
     any
    0.54
    N
    0.53
    POSITIVE LOGITS
     этих
    0.57
    igators
    0.57
     of
    0.50
    uminum
    0.50
     terrib
    0.50
     наших
    0.49
    usive
    0.49
    ibus
    0.49
     lindas
    0.49
    uminium
    0.49
    Act Density 0.035%

    No Known Activations