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

    Neuronpedia

    INDEX
    Explanations

    Python code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ίτ
    -0.07
     reproduce
    -0.07
     insists
    -0.07
    plication
    -0.06
     disdain
    -0.06
    leine
    -0.06
     Brendan
    -0.06
    .ne
    -0.06
    воб
    -0.06
    [%
    -0.06
    POSITIVE LOGITS
     chave
    0.07
     natural
    0.06
     sağlıklı
    0.06
    eração
    0.06
    	TokenNameIdentifier
    0.06
    onitor
    0.06
     vulnerable
    0.06
    스를
    0.06
    .ImageIcon
    0.06
    .shadow
    0.06
    Act Density 0.014%

    No Known Activations