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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _Image
    -0.07
     freight
    -0.06
     paternal
    -0.06
     scenery
    -0.06
    _;
↵
    -0.06
     celery
    -0.06
    协
    -0.06
     desta
    -0.05
     linebacker
    -0.05
     pä
    -0.05
    POSITIVE LOGITS
    ﺮ
    0.07
     plays
    0.07
    ุษย
    0.07
    =sum
    0.06
     threatens
    0.06
    .Dense
    0.06
    рит
    0.06
    .Role
    0.06
    	↵	↵↵
    0.06
    ixel
    0.06
    Act Density 0.057%

    No Known Activations