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

    Neuronpedia

    INDEX
    Explanations

    Spec

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    REET
    -0.08
    -keys
    -0.07
    нд
    -0.07
    reet
    -0.07
     Arbeit
    -0.07
    oned
    -0.07
    ospital
    -0.06
    bdb
    -0.06
     мали
    -0.06
    аю
    -0.06
    POSITIVE LOGITS
     amaç
    0.07
     هنگ
    0.06
    --------------------------------------------------------------------------↵
    0.06
     dictionaries
    0.06
    abilmek
    0.06
    δος
    0.06
    -striped
    0.06
    ,GL
    0.06
     الاح
    0.06
     สถาน
    0.06
    Act Density 0.010%

    No Known Activations