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

    Neuronpedia

    INDEX
    Explanations

    at its core

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     least
    0.89
    起始
    0.75
    least
    0.72
     starting
    0.68
    StartPosition
    0.67
     beginning
    0.67
     slightest
    0.67
     شروع
    0.67
    igram
    0.66
    beginning
    0.66
    POSITIVE LOGITS
    Core
    1.19
     Core
    1.11
    core
    1.04
     core
    1.04
     CORE
    0.94
     heart
    0.91
    CORE
    0.91
     cores
    0.88
     coeur
    0.84
     coração
    0.81
    Act Density 0.033%

    No Known Activations