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

    Neuronpedia

    INDEX
    Explanations

    file named

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     automatically
    0.94
    assembled
    0.80
    automatically
    0.80
     produced
    0.78
     generated
    0.76
     automatisch
    0.75
     reconst
    0.75
    executed
    0.73
     underneath
    0.72
    generated
    0.71
    POSITIVE LOGITS
     তুমি
    0.87
     qualquer
    0.85
     اپنے
    0.82
     deiner
    0.80
     yourself
    0.80
     कुनै
    0.79
     Decide
    0.79
    any
    0.77
     możesz
    0.77
     activiteiten
    0.76
    Act Density 0.105%

    No Known Activations