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

    Neuronpedia

    INDEX
    Explanations

    Parentheses and brackets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     jade
    -0.07
    vron
    -0.07
     Vogue
    -0.07
     까
    -0.07
    یدا
    -0.06
    λον
    -0.06
    .Body
    -0.06
     derog
    -0.06
    Ａ
    -0.06
    quiz
    -0.06
    POSITIVE LOGITS
    oint
    0.07
    stantial
    0.06
    ！↵
    0.06
    strength
    0.06
     outrageous
    0.06
    -shop
    0.06
    輸
    0.06
     emailed
    0.06
    -I
    0.06
     setback
    0.06
    Act Density 0.006%

    No Known Activations