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

    Neuronpedia

    INDEX
    Explanations

    code, test, generation, review

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Switch
    0.49
    Survey
    0.45
    㧍
    0.39
    Grpc
    0.39
    Opened
    0.38
    Picker
    0.38
     Switch
    0.37
     いう
    0.37
    picks
    0.37
    持
    0.37
    POSITIVE LOGITS
     debugging
    1.11
     bugs
    1.09
     bug
    1.07
     debug
    1.06
     Debug
    1.03
    debug
    0.96
     Bug
    0.95
    调试
    0.95
    Debugging
    0.94
    bug
    0.91
    Act Density 0.589%

    No Known Activations