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

    Neuronpedia

    INDEX
    Explanations

    circumstances

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ulen
    -0.06
    .Point
    -0.06
    _redirected
    -0.06
    -stop
    -0.06
    osa
    -0.06
    .iso
    -0.06
     göre
    -0.06
    iyas
    -0.06
    ozem
    -0.06
    -pass
    -0.06
    POSITIVE LOGITS
     verge
    0.07
     guerra
    0.07
    ейчас
    0.07
     engaged
    0.06
     wakeup
    0.06
    ophilia
    0.06
    !..
    0.06
     licked
    0.06
    (train
    0.06
     Discussion
    0.06
    Act Density 0.002%

    No Known Activations