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

    Neuronpedia

    INDEX
    Explanations

    punctuation and special characters in code snippets

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

    code tokens separators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     HARD
    -0.37
     Figue
    -0.35
     VIR
    -0.34
     DEST
    -0.34
     works
    -0.33
    Outbound
    -0.33
    اف
    -0.33
    Hard
    -0.32
     brought
    -0.32
     hard
    -0.31
    POSITIVE LOGITS
     betweenstory
    0.72
    BeginContext
    0.69
     springfox
    0.68
     ddelweddau
    0.68
    Personendaten
    0.67
    GTCX
    0.66
     createState
    0.66
    aarrggbb
    0.65
    Rüyada
    0.61
     GenerationType
    0.61
    Act Density 0.005%

    No Known Activations