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

    Neuronpedia

    INDEX
    Explanations

    project completion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nasıl
    0.54
    h
    0.52
     améliorer
    0.50
     Nasıl
    0.50
     सर्किल
    0.50
     zrobić
    0.49
     bırak
    0.49
    SECTION
    0.48
     mannit
    0.48
    Ned
    0.47
    POSITIVE LOGITS
    懾
    0.54
    TrackedDevice
    0.45
    慑
    0.45
    that
    0.44
    jor
    0.44
    isher
    0.43
    irty
    0.43
     purged
    0.43
    ils
    0.43
     contient
    0.42
    Act Density 0.001%

    No Known Activations