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

    Neuronpedia

    INDEX
    Explanations

    playing cards

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    合理
    -0.08
     stages
    -0.08
     全球
    -0.08
    _stage
    -0.08
    Stages
    -0.08
     decentral
    -0.08
    hik
    -0.08
     staggering
    -0.07
    stellung
    -0.07
    _you
    -0.07
    POSITIVE LOGITS
     Sad
    0.09
     Sep
    0.09
     клав
    0.08
    .Messages
    0.08
     сообщений
    0.08
     melanch
    0.08
     gambler
    0.08
    Sad
    0.08
     mensajes
    0.08
    וגמא
    0.07
    Act Density 0.002%

    No Known Activations