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

    Neuronpedia

    INDEX
    Explanations

    lists and instructions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     de
    0.91
     De
    0.89
    0.80
     Boy
    0.78
    暁
    0.76
    ال
    0.76
     Solution
    0.75
    یل
    0.75
    اك
    0.75
    ک
    0.75
    POSITIVE LOGITS
     siedz
    0.96
     tová
    0.92
     Chí
    0.86
     vattati
    0.83
     afectado
    0.83
     legions
    0.81
    рын
    0.80
     ಅವು
    0.80
     unwa
    0.79
     enemigo
    0.79
    Act Density 0.000%

    No Known Activations