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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Met
    -0.07
     PSD
    -0.07
    標準
    -0.06
     اجر
    -0.06
     Metal
    -0.06
     cytok
    -0.06
     meş
    -0.06
     metabol
    -0.06
    _PLATFORM
    -0.06
    aln
    -0.06
    POSITIVE LOGITS
     rain
    0.06
    _handlers
    0.06
     Latitude
    0.06
     deltaTime
    0.06
     Ironically
    0.06
    込み
    0.06
     successor
    0.05
     observations
    0.05
    _CODEC
    0.05
    客户
    0.05
    Act Density 0.000%

    No Known Activations