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

    Neuronpedia

    INDEX
    Explanations

    explaining code or instructions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cumplir
    0.78
     tiene
    0.76
     tenía
    0.76
     utilizzare
    0.75
     realizó
    0.75
     tienen
    0.74
     cayó
    0.74
     utilizar
    0.73
     가능하다
    0.72
     posee
    0.72
    POSITIVE LOGITS
     stating
    3.58
     indicating
    3.50
     saying
    3.30
     explaining
    3.19
     telling
    3.04
     describing
    2.98
     suggesting
    2.91
     declaring
    2.86
     proclaiming
    2.86
    indicating
    2.78
    Act Density 0.730%

    No Known Activations