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

    Neuronpedia

    INDEX
    Explanations

    Punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     కీల
    -0.07
     ম্য
    -0.07
     ইন
    -0.07
     যৌ
    -0.07
    .l
    -0.07
     ಸಾಕ
    -0.07
     Initialized
    -0.07
    peek
    -0.07
     মাত্র
    -0.07
    ના
    -0.07
    POSITIVE LOGITS
     ???↵↵
    0.09
     forth
    0.09
    ??↵↵
    0.09
     bár
    0.08
    bein
    0.08
    avant
    0.08
     eld
    0.08
    gleichen
    0.08
    ांव
    0.08
    ???↵↵
    0.08
    Act Density 0.165%

    No Known Activations