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

    Neuronpedia

    INDEX
    Explanations

    hesitant opinions or states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    및
    0.81
    Additionally
    0.80
    および
    0.80
    due
    0.79
    及び
    0.79
     మరియు
    0.77
    via
    0.74
     via
    0.74
     તેમજ
    0.74
     प्रदान
    0.73
    POSITIVE LOGITS
    ?...
    0.90
     น่ะ
    0.90
     adesso
    0.89
     наверное
    0.88
    じゃない
    0.87
     huh
    0.86
     Somehow
    0.85
    ่ะ
    0.85
     kinda
    0.84
     alright
    0.83
    Act Density 0.146%

    No Known Activations