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

    Neuronpedia

    INDEX
    Explanations

    terms associated with creativity, clarity, honesty, specificity, and precision in communication

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

    qualities of description

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     avven
    -0.52
     miniaturka
    -0.51
    周泽
    -0.49
    UnusedPrivate
    -0.49
     ļ
    -0.48
    actéristi
    -0.47
    vlád
    -0.47
    好处
    -0.46
     mijne
    -0.46
     indiví
    -0.45
    POSITIVE LOGITS
     Biôgrafia
    0.41
    featureID
    0.40
    帖最后由
    0.39
     joking
    0.39
    zzleHttp
    0.38
    HasForeignKey
    0.37
     autorytatywna
    0.36
    RTHOOK
    0.35
    :✨
    0.35
     fubject
    0.35
    Act Density 0.026%

    No Known Activations