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

    Neuronpedia

    INDEX
    Explanations

    urls and domain names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    朊
    0.25
    牞
    0.24
    𝘞
    0.23
    قيق
    0.22
    thisTrack
    0.22
     родо
    0.22
    穼
    0.21
     Elovl
    0.21
    颞
    0.21
    榈
    0.21
    POSITIVE LOGITS
    i
    0.26
    7
    0.25
    https
    0.24
    def
    0.24
    5
    0.24
    s
    0.24
    0
    0.24
    test
    0.23
    Is
    0.23
    1
    0.23
    Act Density 0.000%

    No Known Activations