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

    Neuronpedia

    INDEX
    Explanations

    Storing imports and specific phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     a
    0.38
    ,
    0.32
    ായ
    0.30
     nello
    0.30
     HID
    0.28
    میں
    0.28
    *
    0.28
     Plata
    0.28
    \
    0.28
    3
    0.27
    POSITIVE LOGITS
     시절
    0.32
    larından
    0.32
    𒊑
    0.31
    ısında
    0.31
    fections
    0.31
    ૂત
    0.30
    द्धाल
    0.30
    Pren
    0.30
    beatCounter
    0.29
    లను
    0.29
    Act Density 0.001%

    No Known Activations