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

    Neuronpedia

    INDEX
    Explanations

    British nobility

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    شه
    -0.06
    jad
    -0.06
    Constraint
    -0.06
     наг
    -0.06
    _SUR
    -0.06
     Vale
    -0.06
     pursuing
    -0.06
     waar
    -0.06
     Sol
    -0.06
    원
    -0.06
    POSITIVE LOGITS
     Olomou
    0.06
     concussion
    0.06
    ǎ
    0.06
     conex
    0.06
    큼
    0.06
     puss
    0.06
    Condition
    0.06
     Ye
    0.06
    猪
    0.06
    .friend
    0.06
    Act Density 0.003%

    No Known Activations