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

    Neuronpedia

    INDEX
    Explanations

    Historical context, years

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ("***
    -0.07
    [int
    -0.06
    Absent
    -0.06
    Mgr
    -0.06
    starttime
    -0.06
     déf
    -0.06
     stand
    -0.06
     sacrifice
    -0.06
    icari
    -0.06
    	act
    -0.06
    POSITIVE LOGITS
    _INTERVAL
    0.06
    HW
    0.06
    label
    0.06
     із
    0.06
     Nintendo
    0.06
    ью
    0.06
     Soros
    0.06
    esis
    0.06
     кіль
    0.06
    ΗΝ
    0.06
    Act Density 0.070%

    No Known Activations