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

    Neuronpedia

    INDEX
    Explanations

    Match

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Sync
    -0.06
     esa
    -0.06
     Cry
    -0.06
    cobra
    -0.06
     pound
    -0.06
     Carrie
    -0.06
    ために
    -0.06
     refrain
    -0.06
    asure
    -0.05
     bson
    -0.05
    POSITIVE LOGITS
    FOUND
    0.07
    IGNED
    0.06
    ]",
    0.06
     hardships
    0.06
    аліст
    0.06
     среди
    0.06
    atorio
    0.06
     minul
    0.06
     Ihrem
    0.06
    (xml
    0.06
    Act Density 0.703%

    No Known Activations