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

    Neuronpedia

    INDEX
    Explanations

    references to chat user interface elements

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

    Java code and foreign words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -0.43
    httphttps
    -0.43
    TokenNameDOT
    -0.37
     CreateTagHelper
    -0.37
    AddTagHelper
    -0.36
    ($__
    -0.36
    RegressionTest
    -0.35
    saraba
    -0.35
    ↘
    -0.34
     ProtoMessage
    -0.33
    POSITIVE LOGITS
     feroit
    0.66
    pulseira
    0.62
    XmlAccessType
    0.61
    carteles
    0.59
     Paglinawan
    0.59
     bénévoles
    0.57
    colgante
    0.57
     avoient
    0.57
     desmotivaciones
    0.57
     pouvoit
    0.56
    Act Density 0.092%

    No Known Activations