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

    Neuronpedia

    INDEX
    Explanations

    question

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    자료
    -0.06
    _FLOW
    -0.06
    employee
    -0.06
    oky
    -0.06
    _pod
    -0.06
    .arr
    -0.06
    .Stream
    -0.06
    Sw
    -0.06
     appropriations
    -0.06
    Dep
    -0.06
    POSITIVE LOGITS
     wxDefault
    0.06
     sincerely
    0.06
     hairstyles
    0.06
     intestine
    0.06
    ujet
    0.06
     Frage
    0.06
    uft
    0.06
     contraception
    0.06
     ／:
    0.06
     applaud
    0.06
    Act Density 0.017%

    No Known Activations