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

    Neuronpedia

    INDEX
    Explanations

    too [adjective] to [verb]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    iot
    1.23
    kan
    1.20
    iere
    1.11
    ع
    1.07
    amination
    1.06
    iempo
    1.06
     ternyata
    1.06
    ič
    1.05
    andaş
    1.05
    ıl
    1.05
    POSITIVE LOGITS
    م
    1.16
    म
    1.05
    י
    1.02
    ز
    1.01
    スム
    1.00
    <0x8C>
    0.98
    ඕ
    0.98
     pranzo
    0.98
     pleasures
    0.97
    ສາມາດ
    0.97
    Act Density 0.019%

    No Known Activations