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

    Neuronpedia

    INDEX
    Explanations

    terms associated with conflict and societal issues

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

    preceding verbs or nouns

    np_acts-logits-general · gemini-2.0-flash

    causes negative outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    HtmlAttribute
    -0.65
    Viited
    -0.53
     sumpay
    -0.49
    macam
    -0.47
    mitting
    -0.45
     without
    -0.44
    lives
    -0.43
    сылкі
    -0.43
    DispatchToProps
    -0.42
    quelles
    -0.42
    POSITIVE LOGITS
     ensures
    1.08
     helps
    1.02
     gives
    0.92
     brings
    0.90
     makes
    0.90
     ensure
    0.88
     enables
    0.88
     helped
    0.88
     sprawia
    0.88
    ทำให้
    0.88
    Act Density 0.577%

    No Known Activations