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

    Neuronpedia

    INDEX
    Explanations

    system design interview solutions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    িলারা
    0.41
    ុំ
    0.39
    itted
    0.38
    umbled
    0.37
    renched
    0.37
    itipi
    0.37
    imeters
    0.36
    ivu
    0.36
    হাসিক
    0.36
    डेट
    0.35
    POSITIVE LOGITS
     solves
    0.47
     solve
    0.46
     Video
    0.46
     Numer
    0.45
     Solve
    0.45
    Q
    0.45
     solved
    0.45
     solving
    0.44
     Q
    0.42
     Sol
    0.42
    Act Density 0.001%

    No Known Activations