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

    Neuronpedia

    INDEX
    Explanations

    references to the audience or the recipients of the message

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

    personal pronouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    LookAnd
    -0.50
     työn
    -0.48
     protestas
    -0.48
    /**
    -0.47
     mudou
    -0.46
    binaan
    -0.46
     aveug
    -0.46
     Olof
    -0.46
    ximately
    -0.46
     zanahoria
    -0.45
    POSITIVE LOGITS
     يتيمه
    0.60
     nakalista
    0.53
    stdc
    0.50
    enterOuterAlt
    0.47
     equipped
    0.44
    RegistryLite
    0.41
    modelBuilder
    0.40
     Equipped
    0.39
    TestBed
    0.38
    ScopeManager
    0.38
    Act Density 0.021%

    No Known Activations