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

    Neuronpedia

    INDEX
    Explanations

    minor, developing, still, large, highly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ید
    0.57
    ঠোর
    0.48
    Indianapolis
    0.46
    นาง
    0.46
    віда
    0.46
    нной
    0.46
    Aws
    0.45
    OUSE
    0.44
    ไว้
    0.44
    oisin
    0.44
    POSITIVE LOGITS
     á
    0.52
     ā
    0.49
     épa
    0.48
     ä
    0.48
     apat
    0.47
     maf
    0.47
     convergent
    0.47
     interact
    0.46
    ,}
    0.46
     å
    0.46
    Act Density 0.001%

    No Known Activations