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

    Neuronpedia

    INDEX
    Explanations

    your computer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ellä
    0.45
    하고
    0.43
    εις
    0.43
     ج
    0.41
     کوي
    0.41
     하고
    0.41
     présenter
    0.39
    ocode
    0.38
     ጨ
    0.38
     budete
    0.38
    POSITIVE LOGITS
    υτό
    0.42
     可
    0.41
    <0x9A>
    0.37
     Świę
    0.37
    Pretty
    0.37
    able
    0.37
    劉
    0.37
     files
    0.36
     "</
    0.36
     Martínez
    0.36
    Act Density 0.000%

    No Known Activations