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

    Neuronpedia

    INDEX
    Explanations

    explains docstrings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    да
    0.53
    ът
    0.52
    balances
    0.50
    に関する法律
    0.49
    edition
    0.48
    со
    0.48
    provides
    0.48
    therefore
    0.47
    ア
    0.46
    рят
    0.46
    POSITIVE LOGITS
     Aku
    0.52
     (!)
    0.52
     Calls
    0.46
     Lua
    0.46
     Undo
    0.44
     Internal
    0.44
    预期
    0.44
     Oko
    0.42
     (~
    0.41
     (@
    0.41
    Act Density 0.016%

    No Known Activations