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
    ولة
    -0.07
    rieving
    -0.06
     شهرهای
    -0.06
    廠
    -0.06
     Airport
    -0.06
    aims
    -0.06
     сахар
    -0.06
     Uran
    -0.06
    ится
    -0.06
    WhatsApp
    -0.06
    POSITIVE LOGITS
    .De
    0.07
    /use
    0.06
     undesirable
    0.06
     uz
    0.06
    .datasource
    0.06
    _lite
    0.06
     unrealistic
    0.06
     verts
    0.06
    ('>
    0.06
    )
↵
↵
    0.06
    Act Density 0.012%

    No Known Activations