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

    Neuronpedia

    INDEX
    Explanations

    model responses about capabilities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Here
    0.60
     هنا
    0.58
     aquí
    0.57
     here
    0.57
     Here
    0.57
    HERE
    0.53
     Aquí
    0.52
     HERE
    0.51
     aqui
    0.50
     tutaj
    0.50
    POSITIVE LOGITS
    hexyl
    0.45
     Talk
    0.40
    concret
    0.40
     programs
    0.39
    adet
    0.38
     функциони
    0.37
     Jared
    0.37
     reviewer
    0.37
    industrial
    0.36
     Junk
    0.36
    Act Density 0.112%

    No Known Activations