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

    Neuronpedia

    INDEX
    Explanations

    federal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    是
    -0.06
     diseases
    -0.06
     Pract
    -0.06
     priest
    -0.06
    まり
    -0.06
     Vertical
    -0.06
    —that
    -0.06
    ξε
    -0.06
    Some
    -0.06
    ीतर
    -0.06
    POSITIVE LOGITS
    AndUpdate
    0.08
    (blog
    0.07
    .DropDownItems
    0.07
     burner
    0.07
     adoles
    0.07
     TypeInfo
    0.07
    /Edit
    0.07
    donnees
    0.06
     Oct
    0.06
     biscuits
    0.06
    Act Density 0.008%

    No Known Activations