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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ó
    0.72
     Chairs
    0.72
    YOU
    0.69
    ---
    0.69
    *
    0.68
     чове
    0.67
    ns
    0.65
    }$
    0.65
    src
    0.64
     Spain
    0.63
    POSITIVE LOGITS
    zunehmen
    0.93
     入っ
    0.93
     Ausnahme
    0.92
    🅻
    0.90
     Cumm
    0.90
     உலோக
    0.90
    踽
    0.89
     Fluss
    0.88
    amam
    0.87
    arup
    0.87
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.