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

    Neuronpedia

    INDEX
    Explanations

    Ukrainian text

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Со
    0.32
    би
    0.31
    Ли
    0.30
    ни
    0.30
    щи
    0.29
     ли
    0.29
     Ли
    0.29
    яз
    0.29
    ри
    0.29
    фи
    0.29
    POSITIVE LOGITS
     muy
    0.39
     añadir
    0.37
     incluyendo
    0.36
     proveedor
    0.34
     añadi
    0.34
     descub
    0.34
     dependiendo
    0.34
     necesito
    0.34
     aplicando
    0.34
     disminuir
    0.33
    Act Density 0.009%

    No Known Activations