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

    Neuronpedia

    INDEX
    Explanations

    citations and references

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    "So
    -0.08
    	me
    -0.07
     graphic
    -0.07
     Metadata
    -0.06
    So
    -0.06
    }}">↵
    -0.06
     `_
    -0.06
     sophisticated
    -0.06
     reset
    -0.06
    	callback
    -0.06
    POSITIVE LOGITS
    onenumber
    0.08
    ротив
    0.07
    shared
    0.06
    _assert
    0.06
    _ADD
    0.06
    _expire
    0.06
    シリーズ
    0.06
    pointer
    0.06
    ใจ
    0.06
    _SELECT
    0.06
    Act Density 0.053%

    No Known Activations