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

    Neuronpedia

    INDEX
    Explanations

    Dense

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    신청
    -0.07
     medication
    -0.07
     authentication
    -0.06
     Mari
    -0.06
    (self
    -0.06
    __.__
    -0.06
     politik
    -0.06
     apologized
    -0.06
    (previous
    -0.06
    eb
    -0.06
    POSITIVE LOGITS
    |M
    0.06
     rend
    0.06
     consequently
    0.06
    :size
    0.06
    .reject
    0.06
     เช
    0.06
    ۲۵
    0.06
    ptest
    0.06
     <=>
    0.06
     '}↵
    0.06
    Act Density 0.002%

    No Known Activations