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

    Neuronpedia

    INDEX
    Explanations

    run out of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     исполни
    0.50
     испол
    0.49
     Evaluating
    0.46
     execute
    0.45
     EXEC
    0.45
     실행
    0.45
     Exec
    0.43
     executing
    0.43
    Executing
    0.43
     executions
    0.43
    POSITIVE LOGITS
    亲
    0.43
    груп
    0.43
     rever
    0.42
    tired
    0.40
    acters
    0.39
    Charl
    0.39
     detail
    0.39
    oule
    0.39
    ἧ
    0.38
    Detail
    0.38
    Act Density 0.006%

    No Known Activations