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

    Neuronpedia

    INDEX
    Explanations

    instances of numerical data or references

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

    such as

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    parsedMessage
    -0.70
     Chwiliwch
    -0.67
    StructEnd
    -0.67
    windowFixed
    -0.64
     Мексичка
    -0.64
     AssemblyCulture
    -0.60
     TextAppearance
    -0.60
     itſelf
    -0.58
    +#+
    -0.57
     coraggio
    -0.56
    POSITIVE LOGITS
     err
    0.35
    kennt
    0.34
    cé
    0.34
    err
    0.33
     ми
    0.32
     Loma
    0.32
     duy
    0.31
    quema
    0.30
    indu
    0.30
     Amy
    0.30
    Act Density 0.008%

    No Known Activations