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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and related syntax in code snippets

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

    js code context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     imageNamed
    -0.53
     Brill
    -0.50
    TagMode
    -0.48
    sic
    -0.47
     Drapeau
    -0.46
    joba
    -0.46
    uint
    -0.46
     sulfuric
    -0.46
     Hallen
    -0.46
    citep
    -0.45
    POSITIVE LOGITS
    _;
    1.63
    _,
    1.33
    _);
    1.27
    _.
    1.24
    _)
    1.21
    _;
    1.20
    _->
    1.16
    _),
    1.10
    _));
    1.01
    _:
    0.99
    Act Density 0.010%

    No Known Activations