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

    Neuronpedia

    INDEX
    Explanations

    Transformer encoder-decoder structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cortos
    0.47
    DATABASE
    0.45
    Glad
    0.43
    Delete
    0.42
     Glad
    0.42
    database
    0.40
    Bathroom
    0.38
    Lost
    0.38
    酲
    0.38
     glad
    0.38
    POSITIVE LOGITS
    FBSDKSettings
    0.42
     presidential
    0.40
     Presidential
    0.40
     unitary
    0.40
     الاجتما
    0.39
    adería
    0.37
     pú
    0.37
     faction
    0.36
     configura
    0.36
     plenary
    0.36
    Act Density 0.002%

    No Known Activations