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

    Neuronpedia

    INDEX
    Explanations

    differentiating symbols used in version control syntax

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

    hyphens and similar separators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    featureID
    -0.48
    MigrationBuilder
    -0.47
     fué
    -0.47
     ſes
    -0.46
    ########.
    -0.46
     głos
    -0.43
     confe
    -0.43
    OuterAlt
    -0.42
    />,
    -0.41
    ⟬
    -0.41
    POSITIVE LOGITS
     -
    1.80
     –
    0.95
     -"
    0.82
     -'
    0.74
     --
    0.74
     −
    0.74
     -\
    0.71
     -(
    0.70
     -,
    0.68
     $-
    0.68
    Act Density 0.044%

    No Known Activations