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

    Neuronpedia

    INDEX
    Explanations

    words related to neural networks and machine learning

    oai_token-act-pair · gemini-2.0-flash

    machine learning

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <bos>
    -0.47
    徵
    -0.45
     k
    -0.44
     kem
    -0.43
    quest
    -0.43
    征
    -0.42
    au
    -0.42
    vgg
    -0.40
     last
    -0.38
     v
    -0.38
    POSITIVE LOGITS
    AddTagHelper
    0.98
     <=",
    0.95
     resourceCulture
    0.86
     CreateTagHelper
    0.86
    InitVars
    0.84
    Personendaten
    0.84
    новниш
    0.81
    tagHelperRunner
    0.81
     Normdatei
    0.80
    makeConstraints
    0.75
    Act Density 1.570%

    No Known Activations