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

    Neuronpedia

    INDEX
    Explanations

    advertisement-related content

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

    are leader

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Aholisi
    -0.70
    Personendaten
    -0.69
    AutoScaleMode
    -0.66
    WebElementEntity
    -0.66
    homonymie
    -0.59
     gainera
    -0.59
    vician
    -0.55
     ainfi
    -0.54
    hashtags
    -0.53
    thmetic
    -0.52
    POSITIVE LOGITS
    MathML
    0.42
     ad
    0.31
    ])))
    0.31
    iam
    0.31
    Ді
    0.30
     zainteres
    0.29
     sumpay
    0.28
    kmäler
    0.28
    }{#
    0.27
    場で
    0.27
    Act Density 0.178%

    No Known Activations