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

    Neuronpedia

    INDEX
    Explanations

    references to text or written content

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

    code and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    oneofs
    -0.62
    Alc
    -0.53
    ัน
    -0.53
    انيف
    -0.53
    DockStyle
    -0.53
    Portale
    -0.53
     muñeco
    -0.52
    +"/"+
    -0.52
    lerle
    -0.52
    .'/
    -0.52
    POSITIVE LOGITS
    \{\\
    0.91
    texttt
    0.65
    makeText
    0.65
     textStatus
    0.64
     strconv
    0.63
    text
    0.63
     \]
    0.60
    ftagPool
    0.60
     Reiki
    0.59
     Lanzarote
    0.59
    Act Density 0.030%

    No Known Activations