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

    Neuronpedia

    INDEX
    Explanations

    purs

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     registers
    -0.07
    ると
    -0.07
     confident
    -0.07
    Region
    -0.06
     portals
    -0.06
    Wifi
    -0.06
    -negative
    -0.06
    _Set
    -0.06
    xCF
    -0.06
    _plain
    -0.06
    POSITIVE LOGITS
    aga
    0.07
     recep
    0.06
     İz
    0.06
    □
    0.06
    úsqueda
    0.06
     Něm
    0.06
    ye
    0.06
     OTHER
    0.06
    餐
    0.06
     غر
    0.06
    Act Density 0.003%

    No Known Activations