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

    Neuronpedia

    INDEX
    Explanations

    occurrences of specific symbols or format indicators in text

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

    java or user after turn start

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    twimg
    -0.40
    archiviato
    -0.36
     dolayı
    -0.36
    Usu
    -0.35
     Rasmussen
    -0.35
     Marcell
    -0.35
     rugby
    -0.33
     Jacobsen
    -0.33
     Liège
    -0.33
    giphy
    -0.33
    POSITIVE LOGITS
    RestController
    1.28
     propOrder
    0.69
     defaultstate
    0.56
    ViewFeatures
    0.56
    HasAnnotation
    0.55
    AddTagHelper
    0.55
    MessageTagHelper
    0.55
    ManagedBean
    0.54
     oprot
    0.54
    ApiController
    0.52
    Act Density 0.000%

    No Known Activations