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

    Neuronpedia

    INDEX
    Explanations

    American

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     хозя
    -0.06
     найбіль
    -0.06
    .Sdk
    -0.06
     cru
    -0.06
     Disk
    -0.06
     rychle
    -0.06
     �
    -0.06
     regenerate
    -0.06
    luví
    -0.06
     jud
    -0.06
    POSITIVE LOGITS
     America
    0.08
     aerospace
    0.07
    mé
    0.07
    pen
    0.07
    αρ
    0.07
     erected
    0.07
    crafted
    0.07
    Simply
    0.07
    American
    0.07
    рек
    0.07
    Act Density 0.002%

    No Known Activations