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

    Neuronpedia

    INDEX
    Explanations

    medical/legal disclaimers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ä¹Łåıªèĥ½
    -0.34
     safely
    -0.30
    壸
    -0.29
     carefully
    -0.28
     properly
    -0.27
    bens
    -0.27
    ä¸įåı¯ä»¥
    -0.27
    è°¨æħİ
    -0.27
     securely
    -0.26
     correctly
    -0.26
    POSITIVE LOGITS
    Advertisements
    0.26
    æİĴ
    0.26
    pedo
    0.25
    fortune
    0.25
     guar
    0.25
    arde
    0.24
    èĴĤ
    0.24
    wards
    0.24
    .tt
    0.24
    Anywhere
    0.24
    Act Density 0.087%

    No Known Activations