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

    Neuronpedia

    INDEX
    Explanations

    numbered list items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <unused1698>
    0.90
     conseille
    0.90
     suspending
    0.89
    暂停
    0.89
     municipales
    0.88
    <unused556>
    0.88
     respaldo
    0.87
    asitriangular
    0.86
    <unused1455>
    0.85
    €˜
    0.84
    POSITIVE LOGITS
    .)
    0.76
       
    0.74
     (
    0.73
                                   
    0.70
     (/
    0.70
     ([
    0.67
    ↵
    0.63
                 
    0.63
     /
    0.61
    ))
    0.61
    Act Density 0.139%

    No Known Activations