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

    Neuronpedia

    INDEX
    Explanations

    Code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     noticing
    -0.06
    ]'
    -0.06
     natural
    -0.06
     ガ
    -0.06
     months
    -0.06
     chips
    -0.06
    Collider
    -0.06
     Setting
    -0.06
    ва
    -0.06
     verse
    -0.06
    POSITIVE LOGITS
     zvlá
    0.08
     LinearLayout
    0.07
     وكانت
    0.07
    حص
    0.07
    twitter
    0.06
    /new
    0.06
    iệ
    0.06
    ораз
    0.06
    (gca
    0.06
     defective
    0.06
    Act Density 0.016%

    No Known Activations