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

    Neuronpedia

    INDEX
    Explanations

    references to actions and processes related to user interaction or data handling

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

    lists numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Numerade
    -0.57
    msgTypes
    -0.52
    GEBURTS
    -0.52
    KURZBESCHREIBUNG
    -0.48
    Manbalar
    -0.48
    -0.46
    jgl
    -0.45
    🟤
    -0.42
    SOUNDBITE
    -0.42
    EndInit
    -0.41
    POSITIVE LOGITS
     humaines
    0.44
     noDo
    0.43
     Bengt
    0.42
    новниш
    0.40
    AddTagHelper
    0.39
    appartamento
    0.38
    DateTimeField
    0.38
     vectorielle
    0.37
    หาย
    0.37
     sociedade
    0.36
    Act Density 0.408%

    No Known Activations