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

    Neuronpedia

    INDEX
    Explanations

    phrases related to defeat or giving up

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

    words indicating finality or continuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Diwedd
    -0.40
     собі
    -0.39
    featureID
    -0.38
    蚪
    -0.38
     onOptions
    -0.36
    RAINE
    -0.34
     Heizung
    -0.33
    }$​
    -0.33
     klart
    -0.32
    olesome
    -0.31
    POSITIVE LOGITS
    0.70
     surla
    0.52
    makeText
    0.50
    مصادر
    0.48
     Normdatei
    0.46
    الحياه
    0.46
    Bukkit
    0.45
    crí
    0.44
    bernate
    0.43
    Perman
    0.43
    Act Density 0.097%

    No Known Activations