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

    Neuronpedia

    INDEX
    Explanations

    historical periods and dates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ah
    0.27
    𝗞
    0.27
     N
    0.25
    𝖗
    0.25
     جميع
    0.25
     estarán
    0.25
     Gao
    0.25
     Y
    0.24
     modList
    0.24
     foe
    0.24
    POSITIVE LOGITS
    periode
    0.25
    I
    0.25
     времени
    0.25
    time
    0.25
    period
    0.25
    xlabel
    0.24
    .
    0.24
    IA
    0.24
    ಬ್ಬಿಣ
    0.23
    use
    0.23
    Act Density 0.318%

    No Known Activations