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

    Neuronpedia

    INDEX
    Explanations

    # sequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↡
    0.35
    ริกา
    0.33
    BURG
    0.33
    መሳሳይ
    0.32
     vattum
    0.32
    वेशन
    0.31
    ंबकीय
    0.31
    फारिश
    0.31
    ovne
    0.31
    𒉣
    0.31
    POSITIVE LOGITS
    ?,?,
    0.43
     et
    0.43
     etc
    0.40
     &
    0.40
     t
    0.39
     S
    0.38
     d
    0.37
     ...
    0.36
     l
    0.36
     ...,
    0.35
    Act Density 0.257%

    No Known Activations