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

    Neuronpedia

    INDEX
    Explanations

    at

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ALS
    -0.09
     температура
    -0.07
    app
    -0.07
     एस
    -0.07
    .snp
    -0.06
     XCT
    -0.06
    fection
    -0.06
    ुँ
    -0.06
    _triggered
    -0.06
    ھ
    -0.06
    POSITIVE LOGITS
     hizmet
    0.06
    !==
    0.06
    교회
    0.06
    cimiento
    0.06
    _CAPACITY
    0.06
     '/');↵
    0.06
    代
    0.06
     초기
    0.06
    liği
    0.06
     волос
    0.06
    Act Density 0.018%

    No Known Activations