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

    Neuronpedia

    INDEX
    Explanations

    dissolving, protecting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ಮೆ
    0.49
     ಕಡಿಮೆ
    0.46
    ಲಿನ
    0.45
    cultured
    0.45
    cB
    0.44
    cG
    0.44
     zelf
    0.43
    xlim
    0.42
    voerd
    0.42
    Benzoimidazol
    0.42
    POSITIVE LOGITS
     in
    0.46
    続けて
    0.46
     moot
    0.46
     tragedies
    0.46
     amazement
    0.44
     obstacles
    0.44
    ↵
    0.43
     moll
    0.43
     thanksgiving
    0.43
     festivals
    0.43
    Act Density 0.000%

    No Known Activations