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

    Neuronpedia

    INDEX
    Explanations

    wire transfers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pesc
    1.12
     allez
    1.10
    imetry
    1.05
     gaan
    1.02
     underway
    1.01
    vog
    1.00
    ocarp
    0.98
     portes
    0.97
     outpatient
    0.96
    ներ
    0.96
    POSITIVE LOGITS
    )
    1.09
    ）
    0.87
    )`
    0.82
    ه
    0.81
     ώστε
    0.80
     ）
    0.75
     रिंग
    0.75
     Tricks
    0.75
    ף
    0.74
     ভিতরে
    0.72
    Act Density 0.000%

    No Known Activations