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

    Neuronpedia

    INDEX
    Explanations

    punctuation and markup symbols often related to formatting or structuring content

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

    mathematical formulas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     huel
    -0.32
     Poh
    -0.31
     должна
    -0.31
    Vue
    -0.29
    RIQUE
    -0.29
    vues
    -0.29
     συ
    -0.29
     registration
    -0.29
    XmlAccessorType
    -0.29
    melidir
    -0.28
    POSITIVE LOGITS
     Italijanski
    0.55
    \{\\
    0.55
     müſſen
    0.52
    EndInit
    0.51
     disambiguazione
    0.50
    Cyfarwyddwr
    0.49
    脚注の使い方
    0.49
     setMessage
    0.49
     normalize
    0.48
    征詢我
    0.48
    Act Density 0.000%

    No Known Activations