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

    Neuronpedia

    INDEX
    Explanations

    States

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Too
    -0.07
     Rodgers
    -0.07
     upside
    -0.06
    алу
    -0.06
    [D
    -0.06
     Зав
    -0.06
    League
    -0.06
     Hun
    -0.06
    ійської
    -0.06
     alliance
    -0.06
    POSITIVE LOGITS
     Plugins
    0.07
    ulos
    0.07
    ังส
    0.06
    FS
    0.06
     Merch
    0.06
    ๊ก
    0.06
    ality
    0.06
     Fortunately
    0.06
    (setting
    0.06
     ภาษ
    0.06
    Act Density 0.003%

    No Known Activations