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

    Neuronpedia

    INDEX
    Explanations

    increasing rating

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     favorables
    0.84
    চ্ছন্দ
    0.84
     remarquable
    0.80
     stabilité
    0.79
     फेव
    0.77
    ámicas
    0.76
     तलैया
    0.74
     limpar
    0.74
    黴
    0.73
    हित
    0.72
    POSITIVE LOGITS
     increase
    1.90
     Increase
    1.81
    Increase
    1.68
    increase
    1.63
     increases
    1.63
     Increases
    1.56
     increasing
    1.51
     increment
    1.45
     aumento
    1.44
     Increasing
    1.42
    Act Density 0.577%

    No Known Activations