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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate belief or conviction

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

    sentence starters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     المعيارى
    -0.73
    BufferException
    -0.71
     Administrativna
    -0.68
    AndEndTag
    -0.64
    aarrggbb
    -0.63
     nonatomic
    -0.63
     esternos
    -0.61
    DoubleQuotes
    -0.60
     exception
    -0.59
     resourceCulture
    -0.59
    POSITIVE LOGITS
    Reprodução
    0.38
    lámpara
    0.33
    árbol
    0.33
     '{@
    0.33
    ABCDEF
    0.32
    Gé
    0.31
     começaram
    0.30
     Վերցված
    0.30
     Ge
    0.30
    …………………………………………
    0.30
    Act Density 0.154%

    No Known Activations