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

    Neuronpedia

    INDEX
    Explanations

    positive affirmation/code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    middle
    -0.07
    Teen
    -0.07
     teenage
    -0.07
    Bias
    -0.07
     olmadığ
    -0.07
     Mill
    -0.06
     כניס
    -0.06
    ��
    -0.06
     Boat
    -0.06
     Tin
    -0.06
    POSITIVE LOGITS
     opinion
    0.08
    坷
    0.07
     PX
    0.07
    _VERIFY
    0.07
     ($(
    0.07
    猜想
    0.07
    旗帜
    0.07
     canyon
    0.07
     `[
    0.07
     argv
    0.07
    Act Density 0.002%

    No Known Activations