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

    Neuronpedia

    INDEX
    Explanations

    positive readiness and agreement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fucking
    0.59
     কারণে
    0.43
     kvůli
    0.42
    怎么办
    0.39
    Damn
    0.39
    Fuck
    0.39
     références
    0.39
    damn
    0.38
    」、
    0.38
    }{|
    0.38
    POSITIVE LOGITS
     :)
    1.60
     🙂
    1.50
     😊
    1.48
     :-)
    1.37
    :)
    1.32
    😊
    1.32
     😄
    1.27
    🙂
    1.27
     😀
    1.26
    :-)
    1.23
    Act Density 0.123%

    No Known Activations