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

    Neuronpedia

    INDEX
    Explanations

    database connection pools

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Rasp
    0.44
    ürn
    0.41
     Sylvester
    0.41
    Syl
    0.40
     Piet
    0.39
    Rasp
    0.39
     елект
    0.38
    ppet
    0.37
    Rh
    0.37
     piet
    0.37
    POSITIVE LOGITS
     pool
    1.45
     pools
    1.30
     Pool
    1.27
    pool
    1.26
    Pool
    1.22
    池
    1.18
     Pools
    1.16
     pooled
    1.14
     pooling
    1.13
     池
    1.05
    Act Density 0.004%

    No Known Activations