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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their variations in different contexts

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

    ast traversal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Personendaten
    -0.51
     كومونز
    -0.47
     Anfitrión
    -0.42
    tvguidetime
    -0.41
    Referanser
    -0.41
    Viited
    -0.41
    Viitteet
    -0.40
    setPreferred
    -0.37
     propOrder
    -0.35
     '{@
    -0.35
    POSITIVE LOGITS
    ốc
    0.46
     Bliss
    0.44
    )_/¯
    0.44
     CRL
    0.44
    Geral
    0.44
    看看
    0.44
     Thistle
    0.44
     Nimbus
    0.43
    0.43
     Broom
    0.43
    Act Density 0.017%

    No Known Activations