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

    Neuronpedia

    INDEX
    Explanations

    or and consequently

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     وغیرہ
    0.53
     usw
    0.48
    などが
    0.46
     itp
    0.46
    之类的
    0.44
     మాత్రం
    0.42
    etc
    0.40
     Etc
    0.39
    などの
    0.39
     등의
    0.39
    POSITIVE LOGITS
     importantly
    1.34
     ultimately
    1.12
     subsequently
    1.05
     preferably
    1.04
     crucially
    0.98
     optionally
    0.97
     indeed
    0.96
     frankly
    0.96
     moreover
    0.93
     consequently
    0.92
    Act Density 0.127%

    No Known Activations