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

    Neuronpedia

    INDEX
    Explanations

    here presentational

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    छ
    0.58
    বস্ত
    0.57
    хема
    0.54
     ডেভেল
    0.51
     refreshments
    0.51
     Madame
    0.51
     పాల్గొన్నారు
    0.51
     عال
    0.51
     планы
    0.50
    を食べ
    0.49
    POSITIVE LOGITS
     here
    1.17
     Here
    1.00
    Here
    0.99
     aqui
    0.98
    here
    0.95
     aquí
    0.87
    heres
    0.86
     aici
    0.84
     voici
    0.84
    以下
    0.83
    Act Density 0.109%

    No Known Activations