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

    Neuronpedia

    INDEX
    Explanations

    Names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ="@
    -0.08
    rost
    -0.07
     моя
    -0.07
    .ser
    -0.07
    cling
    -0.06
     coach
    -0.06
    é
    -0.06
    .take
    -0.06
     iPad
    -0.06
    define
    -0.06
    POSITIVE LOGITS
     içi
    0.06
    lantı
    0.06
    zburg
    0.06
     έχουν
    0.06
    helm
    0.06
    emacs
    0.06
     Boise
    0.06
     Early
    0.06
     reconstructed
    0.05
    ANTITY
    0.05
    Act Density 0.006%

    No Known Activations