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

    Neuronpedia

    INDEX
    Explanations

    recent wins and outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     주기
    0.39
     기간
    0.38
     페
    0.38
     годах
    0.37
     periodicity
    0.36
    年来
    0.35
    ）・
    0.35
     Monat
    0.35
     यात
    0.35
    在這裡
    0.35
    POSITIVE LOGITS
    今回の
    0.93
     এবারের
    0.92
     recent
    0.84
    recent
    0.82
     recientes
    0.81
     이번
    0.78
     recente
    0.77
     reciente
    0.77
     recentes
    0.74
     récent
    0.73
    Act Density 0.010%

    No Known Activations