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

    Neuronpedia

    INDEX
    Explanations

    references to file handling and inclusion in code

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

    Code snippets with file paths and URLs

    np_acts-logits-general · gemini-2.0-flash

    relative file paths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ^=
    -0.51
    arashtra
    -0.48
    互联网档案馆
    -0.47
    auteuil
    -0.46
    oolean
    -0.45
     bolsillo
    -0.43
    FormState
    -0.43
    KeySpec
    -0.43
    MessageState
    -0.42
     décrire
    -0.42
    POSITIVE LOGITS
     './
    1.12
     "./
    1.12
     '../
    1.09
     "../
    1.06
    "./
    1.06
     "../../
    1.00
    './
    1.00
     '../../
    0.98
     "..\..\
    0.96
     '/
    0.95
    Act Density 0.096%

    No Known Activations