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

    Neuronpedia

    INDEX
    Explanations

    wages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    вор
    -0.06
    çu
    -0.06
    isable
    -0.06
    pherical
    -0.06
    луш
    -0.06
    etě
    -0.06
     bán
    -0.06
    -inst
    -0.06
    Launching
    -0.06
    Ent
    -0.06
    POSITIVE LOGITS
     trận
    0.07
    付き
    0.07
    _SEGMENT
    0.07
     ribbon
    0.07
    精神
    0.07
     přip
    0.06
    erty
    0.06
     Єв
    0.06
    neighbors
    0.06
    мів
    0.06
    Act Density 0.012%

    No Known Activations