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

    Neuronpedia

    INDEX
    Explanations

    mind and heart

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     indice
    -0.07
    自称
    -0.07
     -----↵
    -0.07
     Tun
    -0.07
     дет
    -0.07
    _N
    -0.07
     rundown
    -0.07
     ""
↵
    -0.07
    .ADMIN
    -0.07
    	Token
    -0.07
    POSITIVE LOGITS
    _LEVEL
    0.08
    ביקור
    0.07
    ألوان
    0.07
     kulland
    0.07
    걸
    0.07
     redirects
    0.07
    abled
    0.07
    ﳍ
    0.07
     Gefühl
    0.06
    ugeot
    0.06
    Act Density 0.022%

    No Known Activations