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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns, particularly variations of "you" and "us."

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

    углы / "should" forms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rrggbb
    -0.35
    dflare
    -0.34
     saja
    -0.34
    qtt
    -0.33
     ब्रेकडाउन
    -0.32
    insatz
    -0.31
    PONSE
    -0.31
     olvides
    -0.30
     cartaz
    -0.30
     vientre
    -0.30
    POSITIVE LOGITS
    rungsseite
    0.68
    UnknownFieldSet
    0.64
    AnchorStyles
    0.58
    ArgumentParser
    0.55
    AlterField
    0.54
     Italijanski
    0.53
    FTFY
    0.52
    UrlResolution
    0.49
    SequentialGroup
    0.49
    UnitTesting
    0.49
    Act Density 0.001%

    No Known Activations