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

    Neuronpedia

    INDEX
    Explanations

    moving beyond

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    द्य
    0.42
     EX
    0.39
    保持
    0.39
     insertion
    0.38
    EX
    0.38
     జాగ
    0.37
    UTHERN
    0.36
    insertion
    0.35
     Coppa
    0.34
    hrung
    0.34
    POSITIVE LOGITS
     abandoning
    1.48
     esche
    1.45
     abandon
    1.40
     aband
    1.38
    摒
    1.38
    Abandon
    1.35
     abandonar
    1.35
    不再
    1.34
     abband
    1.31
     Abandon
    1.27
    Act Density 0.054%

    No Known Activations