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

    Neuronpedia

    INDEX
    Explanations

    de la Vera, of the Lid

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
        
    0.63
     sheer
    0.61
    :
    0.61
     it
    0.61
     a
    0.60
    ;
    0.60
            
    0.59
    (
    0.59
     communic
    0.58
     put
    0.58
    POSITIVE LOGITS
    篒
    0.83
    ᅴ
    0.81
    䤃
    0.75
    таў
    0.72
    䣰
    0.72
    ৤
    0.71
     Brawl
    0.70
     Sosial
    0.70
    <unused633>
    0.69
    ༸
    0.69
    Act Density 0.448%

    No Known Activations