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

    Neuronpedia

    INDEX
    Explanations

    known for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     New
    0.50
     South
    0.50
     Viel
    0.49
    0.48
     Energy
    0.48
     Mazda
    0.47
    New
    0.46
    ech
    0.45
     Magic
    0.45
     Kraft
    0.45
    POSITIVE LOGITS
     terkenal
    0.97
    著名的
    0.86
     notorious
    0.82
     infamous
    0.82
     famosa
    0.82
     famous
    0.82
     dikenal
    0.82
     famously
    0.81
     مشہور
    0.80
    有名な
    0.78
    Act Density 0.061%

    No Known Activations