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

    Neuronpedia

    INDEX
    Explanations

    references to variable identifiers in programming code

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

    index notation with j

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RenderAtEndOf
    -0.68
     createSlice
    -0.48
    PyExc
    -0.47
    andExpect
    -0.42
    NewGuid
    -0.42
    TokenNameLBRACE
    -0.42
     surla
    -0.40
     IBOutlet
    -0.39
    twimg
    -0.39
    MessageState
    -0.38
    POSITIVE LOGITS
     '\\;'
    0.63
     becauſe
    0.52
     desmotivaciones
    0.52
     miniaturka
    0.50
    Autoritní
    0.49
    fromnode
    0.49
    adeloupe
    0.49
     myſelf
    0.47
     يتيمه
    0.47
     againſt
    0.46
    Act Density 0.153%

    No Known Activations