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

    Neuronpedia

    INDEX
    Explanations

    negative indicators or outcomes often related to legal or formal contexts

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

    U.S. citations with numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     queſta
    -0.61
     للاسماء
    -0.57
     Italijanski
    -0.56
    WillAppear
    -0.56
     Normdatei
    -0.56
     kaarangay
    -0.54
    Spoljašnje
    -0.54
    -0.53
     témoig
    -0.53
     Houſe
    -0.52
    POSITIVE LOGITS
     Abschnitt
    0.30
    quoted
    0.30
     ngo
    0.30
     Abschluss
    0.29
    ByExample
    0.28
     vean
    0.28
     rocas
    0.27
    aminan
    0.27
     lengkap
    0.26
     convierten
    0.26
    Act Density 0.014%

    No Known Activations