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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate complexity and distinctions in situations or arguments

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

    because of / due to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     гран
    -0.35
     اخ
    -0.35
     st
    -0.34
     striking
    -0.33
     Cine
    -0.33
     اف
    -0.31
    谷
    -0.31
     sv
    -0.31
    сер
    -0.31
     رسم
    -0.31
    POSITIVE LOGITS
    CppMethod
    0.64
    -------------</
    0.60
    PreExecute
    0.59
    +#+
    0.57
    出版年
    0.56
    ]")]
    0.56
    StoryboardSegue
    0.54
     Roskov
    0.54
     deswegen
    0.54
     Signalez
    0.54
    Act Density 0.071%

    No Known Activations