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

    Neuronpedia

    INDEX
    Explanations

    start of phrases and titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     printing
    -0.79
     çocuklar
    -0.78
     curiosidad
    -0.78
    Abril
    -0.77
     hypothalam
    -0.77
     asmen
    -0.76
    krishnan
    -0.75
    printList
    -0.75
     isActive
    -0.74
     positively
    -0.74
    POSITIVE LOGITS
    bida
    0.72
     hojas
    0.72
     Hoa
    0.71
    drivers
    0.70
    ulai
    0.70
    stripe
    0.68
    horabuena
    0.67
    mità
    0.67
     واج
    0.67
     OBJ
    0.67
    Act Density 0.002%

    No Known Activations