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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Receive
    -0.07
    ecimal
    -0.07
    тя
    -0.06
     argent
    -0.06
    .Payment
    -0.06
    Write
    -0.06
     */,↵
    -0.06
    stride
    -0.06
     punishments
    -0.06
    _Tab
    -0.06
    POSITIVE LOGITS
     зам
    0.07
     undefined
    0.07
    ắ
    0.06
     worn
    0.06
     recoil
    0.06
     JADX
    0.06
    _RCC
    0.06
     dependence
    0.06
     erotiske
    0.06
    ensible
    0.06
    Act Density 0.007%

    No Known Activations