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

    Neuronpedia

    INDEX
    Explanations

    negative emotions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    اذا
    -0.06
     Pr
    -0.06
    ��️
    -0.06
    дж
    -0.06
    男
    -0.06
     knowledgeable
    -0.06
    Toyota
    -0.06
     está
    -0.06
    underscore
    -0.06
    Service
    -0.06
    POSITIVE LOGITS
    طقة
    0.06
    ReLU
    0.06
     oft
    0.06
     sexuales
    0.06
     commander
    0.06
     vér
    0.06
    _FS
    0.06
     dub
    0.06
     Artifact
    0.06
    .onError
    0.06
    Act Density 0.027%

    No Known Activations