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

    Neuronpedia

    INDEX
    Explanations

    instructional steps

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    कब
    0.46
     trycatch
    0.46
     आजमा
    0.44
    結局
    0.44
    他にも
    0.43
     póź
    0.43
     tận
    0.42
     automating
    0.41
    を活用
    0.41
     последу
    0.41
    POSITIVE LOGITS
     Locate
    0.95
     Now
    0.88
    Now
    0.82
     locate
    0.79
     Carefully
    0.76
     Using
    0.74
    Loc
    0.73
     Determine
    0.72
    locate
    0.72
     Then
    0.70
    Act Density 0.145%

    No Known Activations