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

    Neuronpedia

    INDEX
    Explanations

    say #endif

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    jähr
    -0.07
     ek
    -0.07
     Estados
    -0.07
    .addEventListener
    -0.07
     smashing
    -0.07
     Chlor
    -0.07
     cosmic
    -0.07
     Nhi
    -0.07
    ｼ
    -0.07
     xử
    -0.07
    POSITIVE LOGITS
    LL
    0.08
    Hello
    0.07
     instruction
    0.07
    לל
    0.06
    _AN
    0.06
    棒
    0.06
    ‿
    0.06
    山村
    0.06
    .pre
    0.06
     administrators
    0.06
    Act Density 0.001%

    No Known Activations