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

    Neuronpedia

    INDEX
    Explanations

    samples

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fz
    -0.07
     Dude
    -0.07
    (rc
    -0.06
    ubat
    -0.06
    _course
    -0.06
     Engagement
    -0.06
    이지
    -0.06
    이슈
    -0.06
    ристи
    -0.06
    -To
    -0.06
    POSITIVE LOGITS
    �
    0.08
    促
    0.07
     Conservative
    0.07
    备份
    0.06
     subtree
    0.06
     combine
    0.06
     tentative
    0.06
     pours
    0.06
     calm
    0.06
     worried
    0.06
    Act Density 0.009%

    No Known Activations