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

    Neuronpedia

    INDEX
    Explanations

    concepts related to meaning and value in various contexts

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

    qualities and outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dezelve
    -0.49
     zoude
    -0.48
     Administrativna
    -0.46
    ondes
    -0.44
    卯
    -0.41
     campione
    -0.41
     așa
    -0.40
    rientes
    -0.39
    ðsíða
    -0.39
    tisan
    -0.39
    POSITIVE LOGITS
    enterOuterAlt
    0.70
    ReusableCell
    0.60
     بالنسبة
    0.59
    帖最后由
    0.57
    makeText
    0.55
     bagi
    0.53
    verifyException
    0.51
     unto
    0.47
     everyone
    0.46
    setupUi
    0.46
    Act Density 0.052%

    No Known Activations