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

    Neuronpedia

    INDEX
    Explanations

    SIZE = and glacier collapse

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    喱
    1.51
     Förder
    1.50
     Кроме
    1.39
    жет
    1.39
    ことも
    1.37
    Кроме
    1.35
     Biochemical
    1.35
     Daarnaast
    1.34
    ет
    1.32
    ंमध्ये
    1.30
    POSITIVE LOGITS
    al
    1.36
    aste
    1.35
    sman
    1.24
    ylated
    1.24
    hum
    1.24
    y
    1.23
    l
    1.22
    quela
    1.21
    velocity
    1.20
    hard
    1.20
    Act Density 0.000%

    No Known Activations