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

    Neuronpedia

    INDEX
    Explanations

    questions and queries in a coded format

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

    Q: followed by a question

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Sklici
    -0.47
    Бахар
    -0.47
    kloped
    -0.46
     partagé
    -0.44
    mybatisplus
    -0.42
     esternos
    -0.42
    يكب
    -0.42
     sapin
    -0.41
    eramente
    -0.40
    judgment
    -0.40
    POSITIVE LOGITS
    Question
    0.76
     Question
    0.72
     Q
    0.69
    QUESTION
    0.68
    Q
    0.63
     Questions
    0.62
    Fragen
    0.60
     question
    0.59
     questions
    0.59
    Questions
    0.59
    Act Density 0.062%

    No Known Activations