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

    Neuronpedia

    INDEX
    Explanations

    Out

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ૈ
    0.78
     आलम
    0.73
    arist
    0.67
     forgot
    0.66
    𝟰
    0.66
    ىر
    0.65
     രണ്ട
    0.65
     اث
    0.64
     solder
    0.63
    ोर
    0.63
    POSITIVE LOGITS
     കെ
    0.65
     Loud
    0.62
    整形
    0.62
    쨰
    0.61
    权
    0.59
     விர
    0.59
    權
    0.59
    入場
    0.59
     মুগ্ধ
    0.58
     Santos
    0.58
    Act Density 0.011%

    No Known Activations