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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Brah
    -0.08
    纣
    -0.08
     __________________________________
    -0.07
     undes
    -0.07
     jaw
    -0.07
    睚
    -0.07
     JOptionPane
    -0.07
     tooth
    -0.07
     Yourself
    -0.07
     miscon
    -0.07
    POSITIVE LOGITS
    dığında
    0.08
     وفي
    0.07
     watcher
    0.07
     rápida
    0.07
    推动
    0.07
    了我的
    0.07
     shifting
    0.06
    .address
    0.06
    梦幻
    0.06
    abil
    0.06
    Act Density 0.001%

    No Known Activations