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

    Neuronpedia

    INDEX
    Explanations

    phrases related to scrutiny and challenges in personal relationships

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

    clarity and disclosure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    httphttps
    -0.38
    作为一个
    -0.36
    mes
    -0.34
    这是一个
    -0.34
    是個
    -0.32
     Finanzierung
    -0.31
    是个
    -0.31
     koncer
    -0.31
    وارد
    -0.31
    CHAS
    -0.30
    POSITIVE LOGITS
     propOrder
    0.63
     ujednoznacz
    0.63
     مرئيه
    0.59
    matchCondition
    0.55
     Efq
    0.53
     Paglinawan
    0.51
     disambiguazione
    0.49
     témoig
    0.48
     الحره
    0.48
    DataAnnotations
    0.47
    Act Density 0.005%

    No Known Activations