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

    Neuronpedia

    INDEX
    Explanations

    expressions of uncertainty or lack of knowledge

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

    uncertainty and lack of knowledge

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    참고
    -0.50
     trasmissione
    -0.49
    المناصب
    -0.47
     Monfieur
    -0.46
     snippetHide
    -0.46
     myſelf
    -0.45
     Jefus
    -0.44
     houſe
    -0.43
    ſelf
    -0.43
    ſelves
    -0.42
    POSITIVE LOGITS
    TextBoxColumn
    0.46
    hyrchwyd
    0.39
     TMPro
    0.37
    beho
    0.37
    ByVersion
    0.36
    gradients
    0.36
     enf
    0.34
     Depends
    0.32
     mystère
    0.32
    rungsseite
    0.32
    Act Density 0.170%

    No Known Activations