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

    Neuronpedia

    INDEX
    Explanations

    quantify achievements, automation, leveraging

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    iest
    0.35
    𝗲
    0.34
    inating
    0.33
     aloft
    0.32
    पणे
    0.31
     conglomerates
    0.31
    fu
    0.31
    grained
    0.30
     and
    0.30
    ance
    0.29
    POSITIVE LOGITS
     No
    0.45
     There
    0.42
     You
    0.42
     Ayrıca
    0.40
     Without
    0.39
     Reminder
    0.39
     Not
    0.38
     Actually
    0.38
     Former
    0.38
     Also
    0.38
    Act Density 0.020%

    No Known Activations