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

    Neuronpedia

    INDEX
    Explanations

    file paths

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ап
    -0.07
    (P
    -0.07
     oils
    -0.07
     پیام
    -0.06
     denně
    -0.06
    .ali
    -0.06
     případně
    -0.06
     compilers
    -0.06
     trộn
    -0.06
     Millionen
    -0.06
    POSITIVE LOGITS
    دد
    0.07
    clamation
    0.06
    Tuesday
    0.06
     법
    0.06
    izes
    0.06
    ensible
    0.06
    cname
    0.06
    _J
    0.06
    sects
    0.06
    Controllers
    0.06
    Act Density 0.109%

    No Known Activations