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

    Neuronpedia

    INDEX
    Explanations

    data flow/software

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .WebDriver
    -0.08
     Did
    -0.07
    (frames
    -0.07
    ştir
    -0.07
    阜
    -0.07
     rz
    -0.07
    木地板
    -0.07
    �
    -0.07
    ẽ
    -0.07
    \Web
    -0.07
    POSITIVE LOGITS
     resilient
    0.07
     engage
    0.06
     soften
    0.06
     opposes
    0.06
    protect
    0.06
     exploiting
    0.06
     navigating
    0.06
    intérêt
    0.06
    上线
    0.06
     narciss
    0.06
    Act Density 0.032%

    No Known Activations