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

    Neuronpedia

    INDEX
    Explanations

    am trying

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    కున్నారు
    0.84
    においては
    0.82
    であるが
    0.77
     przedmiot
    0.77
     содержит
    0.76
     являются
    0.76
     посредством
    0.76
    였다
    0.75
     upang
    0.75
    하였다
    0.74
    POSITIVE LOGITS
     gonna
    1.77
     wondering
    1.65
     feeling
    1.59
     getting
    1.47
     afraid
    1.46
     craving
    1.45
     hoping
    1.44
     going
    1.43
     kinda
    1.37
     curious
    1.35
    Act Density 0.303%

    No Known Activations