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

    Neuronpedia

    INDEX
    Explanations

    幕

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     OFFICE
    -0.09
     ضلع
    -0.09
     inet
    -0.08
     domingo
    -0.08
    erei
    -0.08
    denken
    -0.08
    nibus
    -0.08
     cães
    -0.08
    Operand
    -0.08
    edores
    -0.08
    POSITIVE LOGITS
    互动
    0.11
    リア
    0.10
    实时
    0.10
     während
    0.09
     synchronization
    0.09
     tijekom
    0.08
     frenzy
    0.08
     během
    0.08
    -sync
    0.08
     viewer
    0.08
    Act Density 0.008%

    No Known Activations