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

    Neuronpedia

    INDEX
    Explanations

    stored data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SE
    0.60
    CC
    0.55
     maior
    0.54
    BA
    0.54
    SL
    0.52
     coalitions
    0.52
    US
    0.51
    ED
    0.50
     variance
    0.50
    Х
    0.50
    POSITIVE LOGITS
    otro
    0.61
    ismillahirrah
    0.55
    蝣
    0.50
    ى
    0.49
     आप
    0.48
    ้ย
    0.48
     ඉද
    0.47
     කියලා
    0.47
     शेवट
    0.47
    abhavena
    0.46
    Act Density 0.002%

    No Known Activations