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

    Neuronpedia

    INDEX
    Explanations

    code comments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     THEN
    -1.30
    明日は
    -1.28
     سپس
    -1.22
    pherds
    -1.21
     then
    -1.20
    :"",
    -1.20
     metų
    -1.20
     потім
    -1.17
    ført
    -1.16
    帶著
    -1.14
    POSITIVE LOGITS
     and
    2.00
    their
    1.36
     whoſe
    1.23
    ㄷ
    1.19
     Their
    1.17
     jotka
    1.17
     which
    1.16
     until
    1.13
    COUVER
    1.13
    ㅅ
    1.12
    Act Density 0.325%

    No Known Activations