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

    Neuronpedia

    INDEX
    Explanations

    symbols and formatting cues typically associated with emphasis or highlighting in text

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

    bolded numbers and text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.77
    exitRule
    -0.63
     EconPapers
    -0.57
     saites
    -0.51
     utafitiHapana
    -0.51
    writeFieldEnd
    -0.50
     <=",
    -0.50
    ThroughAttribute
    -0.50
    LLocation
    -0.50
    ValueStyle
    -0.49
    POSITIVE LOGITS
     houſe
    0.41
    DoubleQuotes
    0.40
    ）』
    0.38
     (;;)
    0.36
    >()
    0.35
     fuckin
    0.35
    lgari
    0.35
    És
    0.34
     (@
    0.34
     epic
    0.33
    Act Density 0.058%

    No Known Activations