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

    Neuronpedia

    INDEX
    Explanations

    connections between different concepts or ideas

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

    Pronouns and possessive pronouns

    np_acts-logits-general · gemini-2.0-flash

    ones and others

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RegressionTest
    -0.58
    pulumi
    -0.55
    }(),
    -0.55
    templateUrl
    -0.52
     препратки
    -0.52
    IGraphics
    -0.52
     aceste
    -0.52
    mbols
    -0.51
    <?
    -0.49
     viewType
    -0.48
    POSITIVE LOGITS
     ones
    2.98
     ours
    1.80
     yours
    1.77
     Ones
    1.73
     theirs
    1.73
     others
    1.72
     quelli
    1.68
     hers
    1.64
     celui
    1.59
    Ones
    1.52
    Act Density 0.724%

    No Known Activations