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

    Neuronpedia

    INDEX
    Explanations

    initial tokens of words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0
    0.27
    టీఎం
    0.25
    (
    0.24
    jsonplaceholder
    0.24
     emissions
    0.24
     задач
    0.24
    6
    0.23
     externalities
    0.23
    AQP
    0.23
     stressors
    0.23
    POSITIVE LOGITS
    د
    0.43
    ك
    0.36
    א
    0.31
    d
    0.31
     Morocco
    0.30
    p
    0.30
    на
    0.30
    first
    0.30
     foglie
    0.29
    פ
    0.29
    Act Density 0.255%

    No Known Activations