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

    Neuronpedia

    INDEX
    Explanations

    list item markers * and **

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Championship
    0.51
     HDTV
    0.46
     OCLC
    0.44
     çerçe
    0.44
     HDAC
    0.41
     ضد
    0.41
    <span>
    0.40
     জাদু
    0.40
     Scholarships
    0.40
     plasmid
    0.39
    POSITIVE LOGITS
     alguno
    0.51
     evaluar
    0.49
    istika
    0.48
    essentially
    0.48
     cuentas
    0.48
     hermoso
    0.48
     краси
    0.47
     данном
    0.46
    ку
    0.46
    USR
    0.46
    Act Density 0.001%

    No Known Activations