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

    Neuronpedia

    INDEX
    Explanations

    "and" or "then"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Motivation
    0.73
     carénés
    0.70
     Otros
    0.68
     새로운
    0.67
     naranja
    0.66
    สถาน
    0.65
     Otras
    0.64
     Wetland
    0.63
     Notas
    0.63
     Ката
    0.63
    POSITIVE LOGITS
    -,
    0.56
    iness
    0.53
    atre
    0.52
    ),
    0.51
    ubb
    0.51
    -【
    0.51
    our
    0.51
    enge
    0.50
    ier
    0.50
    ister
    0.50
    Act Density 0.001%

    No Known Activations