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

    Neuronpedia

    INDEX
    Explanations

    Breathing, compartment, times, check

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    DAM
    0.48
     shamb
    0.47
    Sach
    0.46
     ಮಹ
    0.45
     declar
    0.44
    KM
    0.44
    MOB
    0.44
     Excelente
    0.44
     möglicherweise
    0.44
     rimu
    0.44
    POSITIVE LOGITS
    亍
    0.46
    序
    0.46
    定价
    0.45
    تك
    0.44
    簹
    0.42
    列
    0.41
    ிறான்
    0.40
     ধরনের
    0.40
    აფ
    0.40
    σεις
    0.40
    Act Density 0.001%

    No Known Activations