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

    Neuronpedia

    INDEX
    Explanations

    questions about subjective judgment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    역시
    0.95
    やはり
    0.95
     denominado
    0.95
     tekint
    0.93
     이러한
    0.89
    또한
    0.88
    どのような
    0.88
    Nous
    0.85
     utiliza
    0.84
     તેમજ
    0.83
    POSITIVE LOGITS
     subconsciously
    1.13
     crappy
    1.09
     hating
    1.05
     unconsciously
    1.03
     objectively
    1.02
     mediocre
    0.97
     sucks
    0.96
     shitty
    0.95
     nagging
    0.94
     rationally
    0.93
    Act Density 0.345%

    No Known Activations