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

    Neuronpedia

    INDEX
    Explanations

    informal contractions and speech

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    gable
    0.29
     لوبو
    0.29
    LOTRE
    0.28
    కరణ
    0.28
    ঞ্জার
    0.28
    lege
    0.27
    codeInput
    0.27
     LEED
    0.27
    gled
    0.27
     FreeBSD
    0.27
    POSITIVE LOGITS
    것
    0.26
     কিনা
    0.25
    ಂದು
    0.25
     acestea
    0.23
    SELF
    0.23
     HEADER
    0.23
     controlar
    0.23
     अपन
    0.23
     Senhor
    0.23
    מ
    0.23
    Act Density 0.029%

    No Known Activations