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

    Neuronpedia

    INDEX
    Explanations

    symbols and mathematical expressions within the text

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

    Numbers followed by brackets

    np_acts-logits-general · gemini-2.0-flash

    `[` followed by punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Ches
    -0.57
     Rueda
    -0.57
    hermes
    -0.55
     Hakim
    -0.53
     Dune
    -0.52
     Thea
    -0.51
     hermes
    -0.50
     wra
    -0.50
    Aya
    -0.49
    Ach
    -0.49
    POSITIVE LOGITS
    .[
    1.61
    ,[
    1.55
    )[
    1.52
    "[
    1.50
    $[
    1.50
    ).[
    1.48
    '[
    1.47
     $[
    1.46
    ?[
    1.45
    /[
    1.45
    Act Density 1.954%

    No Known Activations