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

    Neuronpedia

    INDEX
    Explanations

    sticky rubber

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     വരുന്ന
    0.38
    িস্টার
    0.36
    traverse
    0.36
     Jenkins
    0.35
     Chev
    0.35
     Smoke
    0.35
     института
    0.35
     rampant
    0.34
    Добрый
    0.34
    Jenkins
    0.34
    POSITIVE LOGITS
     discretized
    0.46
     digitized
    0.38
     crece
    0.38
    стоя
    0.37
     accru
    0.37
     molécule
    0.37
    듈
    0.37
     tore
    0.36
    bae
    0.36
    ogn
    0.35
    Act Density 0.000%

    No Known Activations