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

    Neuronpedia

    INDEX
    Explanations

    trick

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ;"><?
    -0.07
     sentiments
    -0.07
     Living
    -0.07
     sense
    -0.07
    енсив
    -0.07
    -being
    -0.06
    bio
    -0.06
     پرداخت
    -0.06
     ><?
    -0.06
     anguish
    -0.06
    POSITIVE LOGITS
     trick
    0.15
     tricks
    0.14
     Trick
    0.13
     Tricks
    0.13
     tricky
    0.10
     Ordering
    0.07
    .C
    0.07
     rigged
    0.07
    Retry
    0.06
    -G
    0.06
    Act Density 0.005%

    No Known Activations