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

    Neuronpedia

    INDEX
    Explanations

    wikipedia links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     necesitamos
    0.45
     संपूर्ण
    0.42
     Якщо
    0.40
     percentuale
    0.39
    兩
    0.38
     possiamo
    0.38
     ตุลาคม
    0.37
     yüzde
    0.36
     потрібно
    0.36
     precisamos
    0.35
    POSITIVE LOGITS
     Airy
    0.37
    ছিল
    0.36
     Diarsipkan
    0.35
     notable
    0.35
    mills
    0.34
     Notable
    0.33
     "^
    0.32
     OCLC
    0.32
    ्ला
    0.31
     Vaux
    0.31
    Act Density 0.005%

    No Known Activations