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

    Neuronpedia

    INDEX
    Explanations

    email headers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ($('#
    -0.08
     didnt
    -0.07
    怜
    -0.07
    裆
    -0.07
    styl
    -0.07
     remed
    -0.07
    _above
    -0.07
     Sugar
    -0.07
    (slug
    -0.07
    _CheckedChanged
    -0.06
    POSITIVE LOGITS
    (order
    0.07
    楽しい
    0.07
    losures
    0.07
    _disc
    0.07
    �
    0.07
    (cards
    0.06
    نك
    0.06
     initiator
    0.06
     office
    0.06
    PEAR
    0.06
    Act Density 0.001%

    No Known Activations