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

    Neuronpedia

    INDEX
    Explanations

    projects

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    уля
    -0.07
    AU
    -0.07
    宿
    -0.06
    데
    -0.06
    AI
    -0.06
    isicing
    -0.06
    Former
    -0.06
    DUCTION
    -0.06
    광
    -0.05
    ระ
    -0.05
    POSITIVE LOGITS
    gets
    0.07
     발
    0.07
     μας
    0.07
    ('-',
    0.07
     Rainbow
    0.07
    _BGR
    0.07
     typename
    0.07
    estination
    0.06
    ,request
    0.06
    senal
    0.06
    Act Density 0.000%

    No Known Activations