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

    Neuronpedia

    INDEX
    Explanations

    Code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    焕
    -0.08
    Toolbar
    -0.08
    alive
    -0.07
    纯净
    -0.07
    (trace
    -0.07
    terra
    -0.07
    嗣
    -0.07
    流逝
    -0.07
    prd
    -0.06
    FRAME
    -0.06
    POSITIVE LOGITS
    опер
    0.08
     Weapon
    0.08
    们的
    0.07
    MESSAGE
    0.07
    .getHeight
    0.07
     Vendor
    0.07
    ksen
    0.07
     spokeswoman
    0.07
    ימה
    0.07
    ungen
    0.07
    Act Density 0.000%

    No Known Activations