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

    Neuronpedia

    INDEX
    Explanations

    say quotation mark/parenthesis

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Drinks
    -0.08
     aan
    -0.07
    (([
    -0.07
    rylic
    -0.06
    ana
    -0.06
     drinks
    -0.06
    Yeah
    -0.06
     kidd
    -0.06
    jde
    -0.06
     explo
    -0.06
    POSITIVE LOGITS
    ่าม
    0.06
     locality
    0.06
    implify
    0.06
    :B
    0.06
    ㅠㅠ
    0.06
    采购
    0.06
    �다
    0.06
     '.$
    0.06
    -dialog
    0.06
    .Sc
    0.06
    Act Density 0.035%

    No Known Activations