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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ﮫ
    -0.08
     ن
    -0.07
    stress
    -0.07
    ussions
    -0.07
    <num
    -0.07
    蹙
    -0.07
    upport
    -0.07
    툭
    -0.07
    Shared
    -0.07
    -0.07
    POSITIVE LOGITS
     İzmir
    0.07
     everlasting
    0.07
     restricting
    0.07
     lite
    0.07
     FormBuilder
    0.07
     eth
    0.06
    谛
    0.06
    记忆
    0.06
    风情
    0.06
    信念
    0.06
    Act Density 0.004%

    No Known Activations