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

    Neuronpedia

    INDEX
    Explanations

    architecture

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	swap
    -0.07
    _gid
    -0.06
     seals
    -0.06
    _prob
    -0.06
    Za
    -0.06
    Cars
    -0.06
     condoms
    -0.06
     continua
    -0.06
    Baby
    -0.06
    okers
    -0.06
    POSITIVE LOGITS
    říž
    0.07
     없었
    0.07
     благ
    0.06
     Arlington
    0.06
    RCT
    0.06
    aji
    0.06
    .mark
    0.06
    거리
    0.06
    ChartData
    0.06
    router
    0.06
    Act Density 0.007%

    No Known Activations