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

    Neuronpedia

    INDEX
    Explanations

    Short connecting words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     arkadaş
    -0.06
    -grand
    -0.06
    аф
    -0.06
     glad
    -0.06
     tr
    -0.06
    urrect
    -0.06
    ísto
    -0.06
    งของ
    -0.06
     histor
    -0.06
    enic
    -0.06
    POSITIVE LOGITS
    ์
    0.08
     Math
    0.07
     Workshop
    0.06
    .TypeString
    0.06
    .loader
    0.06
    迷
    0.06
    吗
    0.06
     путем
    0.06
     Environment
    0.06
    iteDatabase
    0.06
    Act Density 0.232%

    No Known Activations