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

    Neuronpedia

    INDEX
    Explanations

    countries

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    愉悦
    -0.08
    ᴜ
    -0.07
    Always
    -0.07
     MO
    -0.07
     fiance
    -0.07
     echt
    -0.07
    _ALLOC
    -0.07
     nou
    -0.07
     Huss
    -0.07
     hele
    -0.07
    POSITIVE LOGITS
    (dat
    0.07
    represented
    0.07
    ampled
    0.06
     infield
    0.06
    -watch
    0.06
     ใน
    0.06
    Evento
    0.06
     fixes
    0.06
     off
    0.06
    内で
    0.06
    Act Density 0.082%

    No Known Activations