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

    Neuronpedia

    INDEX
    Explanations

    a user and an ai

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    取扱
    0.45
     用
    0.42
     내
    0.39
    を表示
    0.39
    用
    0.38
     വിശദ
    0.38
     Въ
    0.37
     deterioration
    0.37
     利用
    0.37
     기본
    0.36
    POSITIVE LOGITS
    ⋘
    0.51
    hashtag
    0.41
    Veg
    0.40
    ंग्रेस
    0.40
     blessing
    0.39
    雉
    0.39
     bombshell
    0.39
    𝔰
    0.38
    चारिक
    0.38
     hasn
    0.38
    Act Density 0.000%

    No Known Activations