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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nó
    -0.07
    adors
    -0.07
     bò
    -0.07
    aaa
    -0.06
    alo
    -0.06
     Surely
    -0.06
     h�
    -0.06
    Mods
    -0.06
    。那
    -0.06
    ्रमण
    -0.06
    POSITIVE LOGITS
     την
    0.08
     the
    0.07
     Knock
    0.07
     THE
    0.07
    >>>>>>>>
    0.07
     Р
    0.07
     commodo
    0.06
    ليه
    0.06
    orsche
    0.06
    cth
    0.06
    Act Density 0.616%

    No Known Activations