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

    Neuronpedia

    INDEX
    Explanations

    news and media

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _shutdown
    -0.07
    Φ
    -0.07
     WS
    -0.06
    想着
    -0.06
     introducing
    -0.06
    -U
    -0.06
    搭配
    -0.06
    .num
    -0.06
    sti
    -0.06
    翻
    -0.06
    POSITIVE LOGITS
    忪
    0.08
    serrat
    0.08
     obsessed
    0.07
    צהר
    0.07
    кро
    0.07
     UIKit
    0.07
    -scenes
    0.07
    沉重
    0.07
     Arbeit
    0.07
    OID
    0.07
    Act Density 0.060%

    No Known Activations