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

    Neuronpedia

    INDEX
    Explanations

    take back control

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     programación
    0.82
     diosa
    0.81
     programação
    0.80
     คง
    0.80
    0.80
     Inoltre
    0.78
    êmement
    0.77
     weiterhin
    0.76
     hicieron
    0.76
     einst
    0.76
    POSITIVE LOGITS
     Put
    0.77
     exp
    0.76
     TK
    0.72
    goes
    0.70
     Zamora
    0.70
     stark
    0.70
    म्र
    0.69
     so
    0.69
     hovering
    0.68
    kT
    0.68
    Act Density 0.004%

    No Known Activations