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

    Neuronpedia

    INDEX
    Explanations

    digits

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     swollen
    -0.07
    _BUFFER
    -0.07
     vigorous
    -0.07
    Implement
    -0.07
     plaster
    -0.07
     recovered
    -0.07
     Ebony
    -0.07
    �
    -0.07
    🥒
    -0.07
     inspectors
    -0.06
    POSITIVE LOGITS
    isArray
    0.07
     irc
    0.07
    _non
    0.07
     usu
    0.07
    #ga
    0.07
    光伏发电
    0.06
     tech
    0.06
    ᆻ
    0.06
     nulla
    0.06
    악
    0.06
    Act Density 0.015%

    No Known Activations