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

    Neuronpedia

    INDEX
    Explanations

    diagrams and structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    क्षणिक
    0.43
    refundable
    0.42
    ەس
    0.42
    тельного
    0.42
    हारिक
    0.42
    🉐
    0.42
     vehement
    0.41
    क़
    0.41
     egregious
    0.39
     désormais
    0.39
    POSITIVE LOGITS
     |
    0.97
     ↓
    0.84
    ├──
    0.84
    └──
    0.84
    └
    0.84
     |--
    0.83
    |
    0.82
    |-
    0.81
     |-
    0.79
    ↓
    0.76
    Act Density 0.051%

    No Known Activations