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

    Neuronpedia

    INDEX
    Explanations

    AC

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    イト
    0.39
     महादेव
    0.39
     cxd
    0.38
    ulfanyl
    0.36
     ادا
    0.35
    ត្ត
    0.35
    gaxModule
    0.35
    CSharp
    0.34
    netHex
    0.34
    𐰰
    0.34
    POSITIVE LOGITS
     AC
    3.88
    AC
    3.78
     ac
    3.41
     Ac
    3.30
    ac
    3.22
    Ac
    3.13
     एसी
    2.83
     ACR
    2.67
    <0x92>
    2.58
     Acme
    2.48
    Act Density 0.074%

    No Known Activations