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

    Neuronpedia

    INDEX
    Explanations

    references to social identities and roles, particularly in relation to class, race, and gender

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

    people or groups

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Grüsse
    -0.42
    ConstraintMaker
    -0.38
     Füße
    -0.37
    tagext
    -0.36
    ggior
    -0.35
     compagni
    -0.35
     Grüße
    -0.35
     papá
    -0.34
     voeten
    -0.33
     vielmehr
    -0.33
    POSITIVE LOGITS
    ChildScrollView
    0.67
    AnchorTagHelper
    0.50
    stateMutability
    0.49
    SourceChecksum
    0.46
    +#+#
    0.46
    RTLI
    0.45
     BoxFit
    0.45
    msgTypes
    0.44
    httphttps
    0.44
    RegressionTest
    0.43
    Act Density 0.338%

    No Known Activations