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

    Neuronpedia

    INDEX
    Explanations

    buying for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ባቸው
    0.82
    広
    0.82
     అమ
    0.74
    Capability
    0.72
    Proced
    0.72
     capacités
    0.72
    unittest
    0.71
    дачи
    0.71
    тика
    0.70
    0.70
    POSITIVE LOGITS
     Nai
    0.86
     everything
    0.85
     due
    0.84
     boho
    0.83
     shopping
    0.82
     husband
    0.77
     nai
    0.76
     Whether
    0.75
     boyfriend
    0.75
    breath
    0.75
    Act Density 0.000%

    No Known Activations