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

    Neuronpedia

    INDEX
    Explanations

    approved by:

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ῥ
    0.52
    vaa
    0.50
     الأبيض
    0.47
    विज्ञापन
    0.44
    िस
    0.44
     activid
    0.44
     crédito
    0.44
    を楽しむ
    0.44
     нём
    0.43
     کرکے
    0.43
    POSITIVE LOGITS
     veter
    0.51
     intertwined
    0.40
    t
    0.39
    sodium
    0.38
     mathvariant
    0.38
    these
    0.38
    numerical
    0.38
    cest
    0.38
    scale
    0.38
     progn
    0.37
    Act Density 0.001%

    No Known Activations