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

    Neuronpedia

    INDEX
    Explanations

    nor or respectively

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     impactful
    0.47
     самые
    0.45
     информа
    0.43
     conversación
    0.42
     самую
    0.41
     uploads
    0.40
     mentorship
    0.40
     diariamente
    0.40
     bạn
    0.40
    Upload
    0.39
    POSITIVE LOGITS
     adherents
    0.51
     variously
    0.49
    asing
    0.48
    reck
    0.48
    TEGER
    0.45
    oreal
    0.45
    tois
    0.45
    rosion
    0.43
    urer
    0.43
    ades
    0.43
    Act Density 0.008%

    No Known Activations