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

    Neuronpedia

    INDEX
    Explanations

    news articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     сай
    -0.06
     rituals
    -0.06
    _min
    -0.06
     mbedtls
    -0.06
     쿠
    -0.06
     Suppliers
    -0.06
    งแต
    -0.06
     forbidden
    -0.06
     vüc
    -0.06
     “…
    -0.06
    POSITIVE LOGITS
    odel
    0.07
    ]",↵
    0.06
    /port
    0.06
     cupboard
    0.06
    _aa
    0.06
    .addAction
    0.06
     vardır
    0.06
    드리
    0.06
     Öz
    0.06
    DP
    0.06
    Act Density 0.015%

    No Known Activations