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

    Neuronpedia

    INDEX
    Explanations

    Math problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _OCCURRED
    -0.08
    079
    -0.08
    	points
    -0.07
    MATCH
    -0.07
    点
    -0.07
    _POINT
    -0.07
     Point
    -0.07
    POINT
    -0.07
    満
    -0.07
    _ARGUMENT
    -0.07
    POSITIVE LOGITS
     earm
    0.12
     withholding
    0.11
     destinada
    0.11
     withheld
    0.11
     reserves
    0.10
     destinados
    0.10
    .allocate
    0.10
     allocations
    0.10
     destined
    0.10
     destinado
    0.10
    Act Density 0.023%

    No Known Activations