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

    Neuronpedia

    INDEX
    Explanations

    Alex and related names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    UALA
    0.40
     perlu
    0.38
     Arrays
    0.38
     Aaj
    0.37
     picking
    0.37
    obt
    0.36
    ்களை
    0.36
    cket
    0.36
    بی
    0.35
     Jy
    0.35
    POSITIVE LOGITS
    andra
    1.09
    ander
    1.02
    andro
    1.00
    andr
    0.98
    andria
    0.97
    andre
    0.92
    Alexandra
    0.89
    Alex
    0.87
    alex
    0.85
    andar
    0.84
    Act Density 0.004%

    No Known Activations