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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ancias
    -0.07
    annels
    -0.06
    วก
    -0.06
    yling
    -0.06
     monot
    -0.06
    atsby
    -0.06
     présent
    -0.06
    일반
    -0.06
    انيا
    -0.06
    _CONNECT
    -0.06
    POSITIVE LOGITS
     mee
    0.07
    ":
↵
    0.07
     Ear
    0.07
     Ow
    0.06
     iets
    0.06
     lc
    0.06
    (temp
    0.06
     Pro
    0.06
    inactive
    0.06
     help
    0.06
    Act Density 0.093%

    No Known Activations