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

    Neuronpedia

    INDEX
    Explanations

    making choices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    fourths
    0.49
     initially
    0.48
     indicador
    0.44
     suggest
    0.43
     discuss
    0.42
     pursuance
    0.42
     existing
    0.41
     increments
    0.41
     mentions
    0.40
     sólidos
    0.40
    POSITIVE LOGITS
    和大
    0.42
    他和
    0.41
    驾驶
    0.40
     onları
    0.40
    人和
    0.40
     रेश
    0.40
    楝
    0.39
    他们的
    0.39
    艰难
    0.39
    会让
    0.39
    Act Density 0.001%

    No Known Activations