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

    Neuronpedia

    INDEX
    Explanations

    as

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    azen
    -0.07
    present
    -0.07
    fos
    -0.07
     Status
    -0.07
     באמצעות
    -0.07
    叚
    -0.07
     spare
    -0.07
    -weight
    -0.06
    	ev
    -0.06
    ↵      ↵
    -0.06
    POSITIVE LOGITS
    (()=>
    0.08
    咿
    0.07
    _VIDEO
    0.07
    =query
    0.07
     прос
    0.07
    吏
    0.07
     salad
    0.06
     ülke
    0.06
    _job
    0.06
     APA
    0.06
    Act Density 0.000%

    No Known Activations