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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Welch
    -0.07
     mano
    -0.07
    ’ép
    -0.07
    pheric
    -0.07
     fame
    -0.07
    公平
    -0.07
     Уз
    -0.07
     obligated
    -0.07
     여부
    -0.07
     esfera
    -0.07
    POSITIVE LOGITS
     January
    0.10
     September
    0.10
     October
    0.10
    ↵                    ↵
    0.09
     오전
    0.09
     Sunday
    0.09
     December
    0.09
     June
    0.09
     midnight
    0.09
     August
    0.09
    Act Density 0.024%

    No Known Activations