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

    Neuronpedia

    INDEX
    Explanations

    from _

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     is
    0.82
     Fortune
    0.80
     commer
    0.75
     rende
    0.74
     West
    0.74
     Grupo
    0.74
     destro
    0.74
     Pharma
    0.73
     questo
    0.72
    服务
    0.70
    POSITIVE LOGITS
    ة
    1.09
    ن
    1.00
    ات
    0.92
    that
    0.90
    ir
    0.89
     (
    0.89
    available
    0.89
    न
    0.88
    st
    0.87
    vorsch
    0.87
    Act Density 0.000%

    No Known Activations