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

    Neuronpedia

    INDEX
    Explanations

    formal communication context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Lets
    0.36
     And
    0.35
    Let
    0.34
     Directly
    0.33
     Let
    0.31
     Often
    0.31
    "—
    0.31
     lets
    0.31
    .”—
    0.31
     Simply
    0.31
    POSITIVE LOGITS
     attached
    0.36
    0.36
    واں
    0.34
     ,
    0.33
     plight
    0.32
    0.31
     اٹ
    0.31
     según
    0.30
     enclosed
    0.30
    vester
    0.30
    Act Density 0.008%

    No Known Activations