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

    Neuronpedia

    INDEX
    Explanations

    concluding activities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    第一个
    -0.93
    IVersion
    -0.89
     primeras
    -0.89
     początku
    -0.86
    beginn
    -0.85
    第一章
    -0.82
    ladores
    -0.82
    urgie
    -0.81
     пър
    -0.81
    getStart
    -0.80
    POSITIVE LOGITS
     finish
    4.25
     concluding
    4.25
     conclude
    4.22
     concludes
    4.19
     ending
    4.13
     finishing
    3.98
     concluded
    3.83
     wrap
    3.80
     conclusion
    3.78
     finishes
    3.69
    Act Density 0.067%

    No Known Activations