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

    Neuronpedia

    INDEX
    Explanations

    I saw her

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     aforesaid
    0.94
     evidentemente
    0.93
    当時
    0.91
    Synopsis
    0.89
     beliau
    0.89
    bam
    0.89
     consens
    0.88
     Superintend
    0.88
     eloqu
    0.88
     Provincia
    0.88
    POSITIVE LOGITS
    ㄐ
    1.05
    胧
    1.04
    MaxScaler
    1.03
    直流
    0.99
     lowercase
    0.98
     آئینے
    0.95
    ങ്ങൾക്ക്
    0.92
     اكس
    0.92
     प्लेटफॉर्म
    0.91
     mohou
    0.90
    Act Density 0.077%

    No Known Activations