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

    Neuronpedia

    INDEX
    Explanations

    listicles and explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     QUI
    0.43
    hitungan
    0.41
    qui
    0.40
     sempat
    0.40
     waxes
    0.39
     qu
    0.38
     quadratic
    0.38
     cron
    0.37
    helpful
    0.37
     sal
    0.37
    POSITIVE LOGITS
     rapporte
    0.39
    狎
    0.38
    棤
    0.38
    AVOA
    0.36
    cenia
    0.36
    )})$
    0.36
     предназначен
    0.36
     として
    0.35
     Accreditation
    0.35
     thống
    0.35
    Act Density 0.000%

    No Known Activations