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

    Neuronpedia

    INDEX
    Explanations

    here to help

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ol
    0.52
    on
    0.51
    ashe
    0.50
    añas
    0.48
    anzas
    0.47
    )
    0.47
    ו
    0.47
     vucc
    0.46
    iere
    0.46
     лица
    0.46
    POSITIVE LOGITS
    dengan
    0.64
     avec
    0.63
     dengan
    0.61
     ペ
    0.59
    िट
    0.57
     hadir
    0.57
    ە
    0.57
     với
    0.53
     minst
    0.52
     S
    0.51
    Act Density 0.121%

    No Known Activations