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

    Neuronpedia

    INDEX
    Explanations

    Lagrange points

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     aust
    -0.08
    cheon
    -0.07
     Holocaust
    -0.07
    �
    -0.07
    �
    -0.07
     waterfront
    -0.07
    敞
    -0.07
     boast
    -0.07
    ель
    -0.06
    ありますが
    -0.06
    POSITIVE LOGITS
    ߘ
    0.07
    뽈
    0.07
    哲学
    0.07
     svenska
    0.07
    띰
    0.07
    _eta
    0.06
     aiming
    0.06
    姚明
    0.06
    oretical
    0.06
     SubLObject
    0.06
    Act Density 0.004%

    No Known Activations