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

    Neuronpedia

    INDEX
    Explanations

    community development and support

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     abnormality
    0.40
    hamming
    0.39
     untrained
    0.38
     ಗೋ
    0.37
    踰
    0.37
     infraction
    0.37
     orale
    0.37
    umeric
    0.37
     grados
    0.36
    懾
    0.36
    POSITIVE LOGITS
     support
    0.94
     updates
    0.91
     developers
    0.88
     codebase
    0.88
     community
    0.87
    开发
    0.84
    Support
    0.83
     releases
    0.83
     Updates
    0.82
    开发者
    0.82
    Act Density 0.110%

    No Known Activations