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

    Neuronpedia

    INDEX
    Explanations

    expressions related to processes and editing actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    prime factors and value

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    BeginContext
    -0.57
    +#+
    -0.57
    fromnode
    -0.56
    featureID
    -0.55
     resourceCulture
    -0.52
    IUrlHelper
    -0.52
     Савезне
    -0.52
     Италијани
    -0.51
    msgTypes
    -0.51
    windowFixed
    -0.51
    POSITIVE LOGITS
     ویکی‌پدیای
    0.39
    RegressionTest
    0.36
    Nhan
    0.33
     likely
    0.33
    Ken
    0.32
     <<<<<<<<<<<<<<
    0.31
     Ken
    0.31
    Chi
    0.30
    Re
    0.29
     probab
    0.29
    Act Density 0.350%

    No Known Activations