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

    Neuronpedia

    INDEX
    Explanations

    references to other protocols or implementations in a technical context

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

    other / Other

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     transfieras
    -0.60
     चीज़ों
    -0.59
    ftagPool
    -0.57
     AssemblyProduct
    -0.57
     ſind
    -0.57
    دانشنامهٔ
    -0.56
    TypedDataSet
    -0.53
     autorytatywna
    -0.52
    ImageContext
    -0.52
    ffindor
    -0.51
    POSITIVE LOGITS
    ther
    0.58
     Otero
    0.53
     Other
    0.53
    other
    0.52
    er
    0.52
    Other
    0.52
     Moreira
    0.52
    ter
    0.46
     OTHER
    0.45
    topbar
    0.45
    Act Density 0.013%

    No Known Activations