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

    Neuronpedia

    INDEX
    Explanations

    references to geographic locations and neighborhoods

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

    Arabic letters and abbreviations with periods

    np_acts-logits-general · gemini-2.0-flash

    Jabal Omar

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     
    -0.60
     whole
    -0.56
     sp
    -0.53
     entire
    -0.51
    up
    -0.51
     y
    -0.50
     home
    -0.49
     c
    -0.49
     present
    -0.48
    đ
    -0.48
    POSITIVE LOGITS
     يتيمه
    1.73
     مرئيه
    1.01
    DoubleQuotes
    0.93
    rungsseite
    0.86
    UnsafeEnabled
    0.84
    بوابة
    0.84
    AndEndTag
    0.83
    fjspx
    0.81
    المناصب
    0.81
    LEncoder
    0.79
    Act Density 0.003%

    No Known Activations